Loading ToolBench

Reading the current corpus…

wtmcp MCP server · D · ToolBench

wtmcp

A Model Context Protocol server that provides tools for interacting with multiple external services including Bugzilla, GitLab, Google Calendar, Google Docs, Google Drive, and Gmail through a plugin architecture

2026-07-28+STDIO10 tools

58/100

Definition Quality58

Protocol Readiness50

Supportability63

Spec posture

Inferred effective spec 2026-07-28+·current baseline 2026-07-28

Static source inference · medium confidence · detected: Dynamic Client Registration

Deprecated protocol patterns detected

Summary

wtmcp provides 10 Bugzilla tools with consistent naming (verb_noun pattern: bugzilla_search, bugzilla_get_*, bugzilla_create_*, bugzilla_update_*, bugzilla_add_*). All tools have descriptions (avg ~60 chars, within baseline 34-392). Input schemas are present with typed parameters and descriptions. However, output schemas are not documented, LLMs cannot predict response structure for chaining. Parameter descriptions lack format constraints (e.g., date format for 'new_since', enum values for 'status'). Error handling and recovery guidance are absent. No dry-run confirmation for destructive ops (create_bug, update_bug, add_attachment) despite dry_run params existing. Composition is sound: tools are single-responsibility and chainable via IDs.

Tools (10)

bugzilla_add_attachmentwriteauth50/100

Add an attachment to a Bugzilla bug

bugzilla_add_commentwriteauth50/100

Add a comment to a Bugzilla bug

bugzilla_create_bugwriteauth50/100

Create a new Bugzilla bug

bugzilla_download_attachmentwriteauth50/100

Download a Bugzilla attachment and save to file

bugzilla_get_attachmentsread onlyauth50/100

Get attachments for a Bugzilla bug

bugzilla_get_bugsread onlyauth50/100

Get one or more Bugzilla bugs by ID

bugzilla_get_commentsread onlyauth50/100

Get comments for a Bugzilla bug

bugzilla_get_historyread onlyauth50/100

Get change history for a Bugzilla bug

Issues (5)

CRITICALtool ↗

Output schemas not documented. LLMs cannot predict response structure, breaking tool chaining and forcing exploratory calls.

bugzilla_searchbugzilla_get_bugsbugzilla_get_commentsbugzilla_get_historybugzilla_get_attachments

HIGHconstrained-input ↗

Parameter descriptions lack format constraints. 'new_since' accepts string but format (ISO 8601? Unix timestamp?) is unspecified. 'status' and 'priority' lack enum values.

bugzilla_searchbugzilla_get_commentsbugzilla_get_historybugzilla_create_bugbugzilla_update_bug

HIGHrecovery-guide ↗

No error recovery guidance. Tools lack descriptions of failure modes, retryability, or next steps when operations fail.

bugzilla_create_bugbugzilla_update_bugbugzilla_add_commentbugzilla_add_attachment

Recommendations

Document output schemas for all tools. Example: bugzilla_search returns {bugs: [{id, summary, status, assigned_to, ...}], total_count: int}. This enables LLMs to chain results into downstream tools.
Add enum constraints to status, priority, severity, and resolution parameters. Replace 'Filter by bug status' with 'Filter by bug status (one of: NEW, ASSIGNED, REOPENED, RESOLVED, VERIFIED, CLOSED)'.
Clarify date/timestamp format for 'new_since' parameter. Specify 'ISO 8601 format (e.g., 2024-01-15T10:30:00Z)' or 'Unix timestamp in seconds'.
Enhance dry_run parameter descriptions: 'If true, preview the operation without making changes. Use this to validate input before committing.' This signals to LLMs that dry_run is a safety mechanism.
Add error recovery hints to write tools. Example for bugzilla_create_bug: 'On failure, check that product and component exist via bugzilla_search. If assignee is invalid, use bugzilla_search to find valid email addresses.'

Score history

Overall score trend

First recorded score · v2 rubric

58/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	D	58	2026-07-28+	v2