Loading ToolBench

Reading the current corpus…

function-lookup-mcp MCP server · C · ToolBench

← Browse

function-lookup-mcp

github.com/osinmv/function-lookup-mcp

MCP server for searching code declarations and API functions using ctags indexing with SQLite FTS5

<=2025-11-25STDIO3 tools

61/100

Definition Quality66

Protocol Readiness47

SupportabilityNot measured-

Spec posture

Inferred effective spec <=2025-11-25·current baseline 2026-07-28

Static source inference · medium confidence · detected: Logging

Deprecated protocol patterns detected

Summary

Three tools with clear verb-noun naming (search_*, list_*) and reasonable descriptions (100-150 chars). All tools have input schemas with types and descriptions. However, output schemas are completely undocumented, LLMs cannot plan downstream calls or extract structured data. Parameter descriptions lack format constraints, ranges, and examples. No error handling guidance. Missing pagination details despite tools accepting offset/limit. No tool annotations (readOnlyHint). Descriptions are functional but generic, lacking WHEN to use and dependency hints.

Tools (3)

list_api_filesread onlysource verified67/100

List all source files indexed for a specific API.

list_indexed_apisread onlysource verified62/100

List all currently indexed API files. Returns a list of API files that have been indexed and are available for searching.

search_declarationsread onlysource verified70/100

Search for code declarations by name. Returns definitions, declarations, and mentions of the given name.

Issues (5)

CRITICALtool ↗

Output schemas completely undocumented. No description of what fields are returned, their types, or structure. LLMs cannot plan multi-step workflows or extract required data for chaining.

search_declarationslist_indexed_apislist_api_files

HIGHconstrained-input ↗

Parameter descriptions lack actionable constraints. 'offset' and 'limit' have no documented ranges (e.g., 'limit: 1-100, default 10'). 'name' parameter in search_declarations has no format guidance (case-sensitive? regex? partial match?).

search_declarationslist_api_files

HIGHrecovery-guide ↗

No error handling guidance. Tools do not document what happens on invalid input (e.g., api_name not found, offset > total results). No recovery hints for LLMs.

search_declarationslist_indexed_apislist_api_files

MEDIUMtool-description ↗

Recommendations

Document output schema for each tool. Example for search_declarations: 'Returns array of {name: string, file: string, line: number, kind: string}. Total count included for pagination planning.'
Add range constraints to numeric parameters: 'offset: 0-999999 (default 0)', 'limit: 1-100 (default 10)'. Add format guidance to string params: 'name: case-insensitive substring match'.
Add error handling guidance: 'If api_name not found, returns empty list. Call list_indexed_apis() to see available APIs.' Include actionable recovery steps.
Enhance tool descriptions with discovery hints: 'Call list_indexed_apis() first to see available APIs, then search_declarations() to find specific code. Use list_api_files() to explore a single API's structure.'
Add tool annotations to schema: readOnlyHint=true for all three tools. Document idempotency: 'Safe to retry; no side effects.'

Spec posture evidence

Inferred effective spec: <=2025-11-25.

Relies on Logging (deprecated) - log to stderr or use OpenTelemetry

Score history

Overall score trend

First recorded score · v2 rubric

61/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	C	61	<=2025-11-25	v2