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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered structurally. The description adds the request shape and the razonada-conditional format rule, which is useful, but says nothing about latency, cost, or the non-determinism an LLM-backed 'razonada' agent implies despite the idempotentHint=true annotation. No contradiction, but limited added behavioral context.

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-loads the endpoint and body shape in a few dense sentences with no filler. It loses a point for duplicating the format enum and conditional rule that the schema already states, which is wasted space rather than new information.

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?

An output schema exists, so return values need not be explained, and the description covers endpoint, body, the conditional format rule, and agent_name resolution. The only real gap is the absence of any routing guidance against the closely related multi_document.ask sibling.

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 description coverage is 100%, so the baseline is 3. The description largely restates what the schema already documents — the format enum list and the 'required only for razonada agents' rule appear verbatim in both places — and adds no syntax, naming, or slug-resolution detail beyond it.

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?

Names a specific verb+resource ('Ask a Retrieve agent') and pins it to the POST /retrieve/{agent_name} endpoint, so the action is unambiguous. It does not distinguish itself from the sibling claix.multi_document.ask, which also asks questions, so an agent cannot route between the two from the text alone.

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?

Usage is only implied ('ask a Retrieve agent'), with one conditional rule carried over from the schema (format required only for razonada agents). There is no statement of when to pick this over multi_document.ask or any other extract/ask sibling, and no prerequisites beyond the api_key note that lives in the schema.

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