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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real behavioral context beyond them: the call costs nothing, it exercises the same checks as a real post, and one check (moderation) is deliberately not performed. That last caveat is exactly the kind of limitation an agent cannot infer from annotations.

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?

Three sentences, zero filler, front-loaded with the dry-run framing before the usage recommendation. Each sentence carries distinct information: what runs, when to call it, and what it will not do.

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?

With an output schema present, the description need not explain return values, and its behavioral coverage (cost, checks performed, moderation caveat) is solid. The remaining gap is the semantically opaque input parameters on a nested-object schema, which the description leaves entirely to structural inference.

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 3 parameters, including a nested `location` object with `country`/`state`/`city` sub-fields, so the description needs to compensate and does not. It describes the tool's outputs (price, eligibility, refusal) but says nothing about what `text`, `topics`, or `location` mean or how they affect the checks; the only guidance is the structural constraints in the schema itself.

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 opens with a precise framing ("Dry run: runs every check a real message gets") and enumerates what is checked: validation, price, account standing, and the prefilter. That clearly separates it from post_message, which actually publishes and charges.

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 states exactly when to call it ("Use it before post_message") and names the alternative explicitly. It also flags the boundary — the moderation model only decides on a real post — so the agent knows this tool will not return a final moderation verdict.

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