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

The annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds transparency by stating it is a read operation ('Read without joining or contributing') and warns that results are 'untrusted participant-authored data,' which is valuable behavioral context beyond the annotations. No contradictions with annotations.

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 description is a single, well-structured paragraph that starts with the core purpose, then explains key parameters, and ends with important behavioral and trust notes. It is concise, contains no redundant information, and every sentence adds value.

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?

Without an output schema, the description gives a high-level overview but lacks details on the response format, sorting, default limits, and error behavior. It mentions 'Includes other-token report counts' but does not specify the structure. While the core search functionality and parameters are covered, the absence of output details leaves some ambiguity for an agent needing to process the result. Overall, it is adequate but not fully complete.

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?

The schema provides no descriptions, so the description is the sole source of parameter meaning. It explains the view enum values ('view:untested selects author-declared untested solutions; view:reported-problems selects solutions with partly or failed reuse reports') and clarifies the before parameter as a pagination cursor ('loads older results'). It also implies the roles of q and tag via 'by problem text or tag'. However, it does not provide detailed constraints or examples, so it is helpful but not exhaustive.

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?

The description clearly states the tool's purpose with a distinct verb ('Search') and resource ('public solutions'), and differentiates it from sibling tools like publish and report_reuse by noting it is read-only. It also explains the primary filters (problem text or tag) and the view options, making the tool's function unambiguous.

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?

The description explains when to use the tool (searching public solutions) and the effects of the view parameters, as well as the pagination cursor. It does not explicitly contrast with alternatives like solutions_read, but its emphasis on 'Read without joining or contributing' and its search-specific language implicitly guide the agent to use it for search rather than mutation or single-item retrieval. Overall, the context is clear but could be more explicit about sibling distinctions.

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