Loading ToolBench
Exposes the Pulse knowledge base as MCP tools for AI coding agents. Any MCP-compatible tool (Claude Code, Cursor, etc.) can query and contribute to the team's operational memory.
Pulse MCP has well-structured tool definitions with clear naming (verb_noun pattern: pulse_search, pulse_create, pulse_delete) and comprehensive descriptions (150-250 chars each). All 6 tools have input schemas with typed parameters and enums where appropriate. However, output schemas are not documented in the source, parameter descriptions lack actionable constraints (e.g., no format hints for git commit hashes), and error handling guidance is absent. The pulse_create tool has complex nested 'structured' parameter that lacks clear documentation of kind-specific field requirements. No tool annotations (readOnlyHint/destructiveHint) despite clear risk levels (READ_ONLY, WRITE, DESTRUCTIVE).
Get relevant context from the knowledge base for a topic or question. Uses semantic search to find the most relevant insights, even if exact words don't match. Use this when starting work on a topic to understand past decisions and avoid known dead-ends.
Record a new insight in the team's knowledge base. Use this when you make a technical decision, discover a dead-end, identify a reusable pattern, complete a milestone, or capture a business requirement/domain constraint that drove a technical choice. Insights are created as drafts and can be published later.
Delete a draft insight. Published insights cannot be deleted (they can be superseded instead).
Get all insights related to a specific file. Use this when you're about to modify a file to understand the decisions, patterns, and dead-ends associated with it.
Publish a draft insight to the team's knowledge base. Once published, it becomes visible to all team members and AI agents.
Output schemas not documented. LLMs cannot plan downstream calls or extract required fields (e.g., insight IDs from pulse_create response needed for pulse_publish).
pulse_create 'structured' parameter lacks kind-specific field documentation. Decision type requires 'why' and 'alternatives' array, but schema does not specify structure or validate nested fields.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite clear risk levels. pulse_delete is destructive but unmarked; pulse_search is read-only but unmarked.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 61 | 2026-07-28+ | v2 |
Search the team's knowledge base for insights — decisions, dead-ends, patterns, and progress. Use this before making technical decisions or when you encounter a problem that may have been solved before.
Parameter constraints lack actionable format hints. 'commit_hashes' requires 'full 40-char' but no regex pattern or minLength constraint in schema. 'file_path' example 'api/src/services/auth.ts' in description may be reused literally by LLM.
No error handling guidance. Tools do not document retryable vs. fatal errors, recovery steps, or what to do if an insight ID is invalid or already published.