Query lessons for diff context

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate read-only and idempotent. Description adds retrieval method (bi-encoder + severity-weighted scoring), token budget, and output format. However, it omits mention of the default value discrepancy for max_tokens (description says 2000, schema says 3000).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first front-loads purpose, second adds technical detail and usage guidance. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given schema coverage and annotations, description explains output format and when to use. Lacks explanation of top_k and project_id, but schema covers them fully. Could briefly mention the ranking mechanism.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage, so baseline is 3. Description adds context about token budget and retrieval method, but contradicts schema by stating max_tokens default is 2000 instead of 3000. This inconsistency reduces reliability for the agent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool retrieves lessons relevant to a code diff or PR context, using specific verb 'retrieve' and resource 'lessons'. Distinguishes from sibling list_lessons by mentioning unfiltered browsing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises using this tool before writing a fix or opening a PR, and recommends list_lessons for browsing all lessons. Also specifies the query input as diff/description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.