Search manual pages

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

With no annotations, the description carries the behavioral burden. It discloses that results are ranked and include a snippet around the first hit, which gives some transparency. However, it does not mention behavior such as default result count, ordering specifics, or empty-result handling. For a simple read-only search tool, this is acceptable but not rich.

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 two sentences, front-loaded with the core purpose, and every sentence contributes useful information. It includes the result format and parameter usage without fluff, achieving maximum conciseness.

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?

For a straightforward search tool with a simple schema and no output schema, the description adequately covers purpose, result format, and key parameter semantics. It lacks an explicit mention of alternative tools, but the sibling list and clear naming make the scope obvious. A more detailed note on return value structure or pagination might be nice, but is not essential for this level of complexity.

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 covers 100% of parameters, so the baseline is 3. The description adds value beyond the schema by explaining the numeric section meanings (2=syscalls, 3=libc, etc.), which is not in the schema's enum descriptions. It also clarifies that the snippet is around the first hit, which relates to query interpretation. This extra guidance justifies a 4.

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 searches the 4.2BSD manual pages and returns ranked matches with snippets. This distinguishes it from siblings like search_documents (general documents) and search_source (source code), while also contrasting with read_manpage (reading a full page). The verb 'search' and resource are specific and 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 provides clear context: it is for searching manual pages, and the section restriction guidance (e.g., 2=syscalls, 3=libc) is helpful. It does not explicitly reference alternative tools or state when not to use it, but the naming and content implicitly differentiate it from sibling search tools. A brief note about using search_source for source code would earn a 5, but the current guidance is adequate.

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