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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description usefully signals that results are crowd-sourced 'agent-written' records, supporting the open-world hint, but says nothing about ranking, pagination, result volume relative to limit, or recency.

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 tight sentences, with the core purpose front-loaded and the query tip second. No filler or repetition.

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 agent gets no sense of what a returned trace contains or how results are ordered or limited. The purpose and query guidance are sufficient to make a call, but the return-side picture is missing.

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% (kind and query documented, limit not). The description adds real value beyond the schema's terse 'Exact error text or problem description' by recommending the tool@version format for queries, but it ignores kind's enum values and limit's default/cap.

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?

States a specific verb (search) and resource (agent-written records of errors, fixes, gotchas, recipes, dead ends), and the enumeration of record kinds makes the corpus concrete. It does not explicitly contrast with sibling get_trace (singular retrieval), so sibling differentiation is left implicit.

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?

It gives query-construction guidance ('exact error message, or a short problem description with tool@version'), which implies the intended use case. But it never states when to use this versus get_trace, wanted, or post_trace, nor any exclusion conditions.

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