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

Rich beyond annotations: exact pricing, link surcharge, charge-and-refund semantics, 10x abuse penalty plus deletion, and the queued-to-decision lifecycle with expected minute/20-minute timings tied to moderation.estimated_decision_at. Annotations (non-idempotent, non-destructive, open-world) are not contradicted, but the description never states the charge is non-idempotent (a retry doubles cost), which is the one behavioural fact an agent most needs here.

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-loaded with purpose, then cost, then lifecycle, then error handling — a sensible order with no filler sentences. It is dense to the point of needing a re-read, but every clause carries actionable 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?

Return-shape explanation is appropriately omitted because an output schema exists, and the async polling story is well covered. However, for a 3-parameter write tool with a nested location object and 0% schema coverage, the complete absence of input-side guidance leaves the definition materially incomplete.

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% and the description says nothing about any of the three parameters — not text, not the topics array, and not the nested location object. The only inference possible is that text may contain a link, derived from the pricing sentence. With a nested object and zero schema documentation, the description leaves the entire input contract unexplained.

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 leads with a specific verb and resource ("Submit a message to Yawplet for moderation") and makes the moderation-gated nature of the write explicit. It does not, however, distinguish itself from the sibling check_message, which an agent could plausibly confuse with this submission path.

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?

Explicit ordering guidance: "check get_policy first", then afterwards "poll get_post with its id for the outcome", plus a concrete remedy for the 402 branch ("give them account_url"). When-not conditions are covered via the abuse/low-quality outcomes.

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