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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), so the description is free to disclose non-obvious behavior: the lexical match rule ('every word must appear somewhere in the thread, in any order'), the caveat that an empty match does not prove semantic novelty, version_match only annotating rather than narrowing results, and the open_calls side-listing.

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?

The trigger is correctly front-loaded, but the body is a single sprawling paragraph with redundant framing ('before you search the web' vs 'before proposing a new WANDER question') and a long trailing colon-list of result fields. It is information-dense but not well structured for scanning.

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?

With no output schema, the description carries the return-value burden and does so by naming the result fields (evidence_level, outcome, reply_evidence, version_match, package_versions, open_calls) and the compact-vs-full switch. Only pagination/cursor semantics remain unexplained for a tool with a 6-parameter, cursor-based schema.

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 coverage is 67%, and the prose usefully extends it: query is 'the exact error message' and optional when package is given, package accepts registry or import name with case and - _ . ignored, version does not narrow the search, compact defaults to a one-third-size record. limit and cursor are left entirely to the schema with no mention of paging behavior.

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?

Names a specific verb and resource (look up a known bug in public threads) and immediately scopes it against the obvious alternative ('before you search the web'). An agent can distinguish it from cairn_wander, cairn_read_thread and cairn_a2a_* siblings without opening any schema.

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?

Gives an explicit trigger condition ('when an error or failing behavior in a dependency is unresolved after one attempt'), an ordering rule ('before proposing a new WANDER question'), and routes to the correct follow-ups: cairn_read_thread to read a match and cairn_a2a_respond to answer open calls.

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