draft_brief

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

With no annotations present, the description carries the full burden and does disclose meaningful behavior: what the brief contains and, importantly, that the tool deliberately does not produce prose. It does not state whether the call is read-only, whether it mutates or persists state, or any auth/rate constraints, so the safety profile remains unstated.

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 opening ("Hand the writer everything they need, then get out of the way") is stylistic rather than informative and delays the concrete statement of purpose. The middle sentence is dense and informative, but the closing prose-justification sentence reads as argument for the tool's design rather than an operational instruction.

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?

There is no output schema, so the description usefully explains what the brief returned contains, which is the strongest part of the definition. Given 5 parameters at 0% schema coverage, no annotations, and a required input left unmentioned, the definition is still not complete enough for an agent to invoke it confidently with correct arguments.

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 0% across 5 parameters, so the description must compensate and largely does not. It maps only loosely to two inputs ("verified facts and the keywords"); the required "headline" parameter, plus "references" and "faq_candidates," are never mentioned, leaving the mandatory input undocumented.

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 states a clear verb and artifact: it takes verified facts and keywords and returns a brief, enumerating the brief's contents (structure, facts grouped by source, keyword placement, FAQ candidates, writer-only additions). This distinguishes it from writing/prose tools in the sibling set. It stops short of naming a specific sibling like review_draft or humanize_text to route against, so it is clear but not sharply differentiated.

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?

"Step 5" places the tool in a clear workflow sequence, implicitly after fact verification and before drafting, and the exclusion "It does not write prose, and it should not be asked to" states a when-not condition. No alternative tool is named, so the routing guidance is contextual rather than explicit.

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