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

Annotations only declare readOnly=false, idempotent=true, destructive=false. The description goes well beyond: it specifies the required auth (TechFabric engineer's Microsoft sign-in, scope blog.write, site owner's only, with the reason 'the brief automation runs as him'), states refusals store nothing, that 'the same topic again is the same brief' (matching idempotentHint with explanation), and that drafts and publishes nothing.

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?

Two sentences, no filler, with auth prerequisites front-loaded before behavior. The second sentence is dense — semicolon-separated refusal clauses and a trailing 'no model' fragment — but every clause carries 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 needn't be explained. Auth, refusal semantics, idempotency, and side-effect limits (nothing drafted or published) are all covered, which is everything an agent needs to invoke this mutation correctly.

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 83%, so the schema already documents all six parameters thoroughly, including 'why' and 'for_author'. The description enumerates the fields (topic, why, angle, sources, target_query, for_author) but adds little meaning beyond what the schema descriptions carry, and the key constraint that topic dedupes against existing work is behavioral rather than parameter-level. Baseline 3 fits.

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?

'Adds one brief to the pool get_brief offers engineers' states a specific verb and resource and ties it to the consuming sibling, so an agent can distinguish it from get_brief, get_brief_pool, and start_post without opening a schema.

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?

It enumerates the refusal conditions precisely (live post or idea in flight covers it, an open proposal already is it, today's 3 are used) and names the consuming sibling get_brief. What's missing is a positive 'call this when you have work worth turning into a brief' framing, but the downside cases are explicit.

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