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

With no annotations, the description carries the full burden and does real work: it discloses that answers are grounded and cited, that the tool refuses rather than guesses when nothing relevant is found, and that it is rate-limited per IP. It omits auth/permission requirements and any sense of latency or result shape, but the refusal and rate-limit disclosure is substantive.

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?

Three short sentences with zero filler, and the core purpose is front-loaded before the behavioral caveats (refusal, rate limit). Every clause earns its place.

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 one-parameter question-answering tool with no output schema, the description covers what it does, the answer style, and the refusal/rate-limit behavior. The main missing piece is any routing hint toward the sibling structured tools, which an agent would need to pick correctly between them.

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?

There is a single parameter with 100% schema description coverage ('A question about Renan or BIS'), so the schema already documents it. The description's 'specific question' phrasing adds a mild quality hint about how to phrase input, but no format or length guidance, matching the baseline 3 when the schema does the heavy lifting.

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 gives a specific verb ('ask a question') and resource ('Renan or BIS'), and 'grounded, cited answer from the BIS assistant' makes clear it is a free-form Q&A tool rather than a structured getter like get_bis_overview or list_services. It never names a sibling explicitly, so the differentiation is implicit rather than stated.

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?

'Ask a specific question about Renan or BIS' implies the usage context, and the refusal clause hints at a boundary condition. However, it gives no explicit when-not guidance and never points to the sibling tools (get_bis_overview, get_case_studies, etc.) that should be used for structured lookups instead.

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