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

Annotations already declare readOnly, idempotent, closed-world, and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral facts: it makes no model calls (deterministic, no inference cost) and it produces two artifacts, a brief to act on and an annex the caller must save. It does not clarify why a read-only tool yields an artifact to persist, but the output schema covers return shape.

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 with the imperative 'Call first' front-loaded, then the return contents enumerated in a single list. Some phrasing is jargon-heavy ('taste questions', 'craft rubric and gates') but every clause carries information; no filler.

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 no further explanation, and annotations cover safety. The description supplies the missing ordering guidance and the no-model-calls cost signal. The remaining gap is parameter-level guidance for request, category, and site_url, which is the main incompleteness for a 5-parameter tool.

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 only 40%, with request, category, and site_url carrying no schema descriptions, so the description must compensate and largely does not. It indirectly echoes the deliverable_kind enum via 'page, ad, copy, email, audit or analysis' and hints at site_url with 'the client's real site or data', but never explains what belongs in request or category, leaving three of five parameters ambiguous.

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 concrete outcome: a short brief to act on plus an annex to save, containing capture instructions, taste questions, default mode, rubric/gates, and AI defaults to avoid. It positions itself as the 'call first' grounding step, which distinguishes it from downstream siblings like start_job or advance_job, though it never names those siblings explicitly.

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?

'Call first for any page, ad, copy, email, audit or analysis' gives a clear trigger condition tied to deliverable types. There is no explicit when-not guidance or named alternative for cases where grounding is unnecessary, which keeps it below a 5.

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