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

Annotations only declare readOnlyHint and idempotentHint, so the description must carry the rest — and it does: cross-module ranking, the shape of each result (id, URL, dates, matching snippet rather than full content), and the partial-coverage caveat that explains why results may be incomplete. This is disclosure an agent cannot get from the annotations or schema.

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?

Front-loaded with purpose and routing before syntax details, and every sentence carries information. The 40-item module slug list is bulky and visually dominates the block, though it is genuinely necessary for the untyped 'modules' array.

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 10-parameter cross-module search with no output schema, the description covers routing, query syntax, result shape, and the coverage caveat, while pagination, date filters and response_format are fully documented in the schema. Nothing an agent needs to call this correctly 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 already 100%, so the baseline is 3, but the description adds query-language semantics absent from the schema: plain words ranked by match count, "exact phrase", +required, -excluded. It also enumerates the valid module slugs for the 'modules' array, which the schema does not constrain. It does not explain cursor paging or the limit ceiling beyond what the schema already says.

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?

Opens with a specific verb and scope: 'Search the content of everything you can read in this Raq.com account in one call', plus states results are ranked across modules with id, URL, dates and a snippet. It explicitly distinguishes itself from both siblings by routing full-record reads to raq_fetch and tool discovery to raq_search_tools.

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 explicit alternatives with the condition that selects each ('Read a result in full with raq_fetch'; 'To find tools rather than records, use raq_search_tools'), and adds strategic advice to prefer several short specific searches over one long question. It also warns that 'coverage lists modules that were not searched and why, so a missing result is not proof that something does not exist', which prevents a common false-negative conclusion.

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