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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds value the annotations cannot: it is free (no credit cost), and it discloses the return contract — "ok is true when there are no errors; each finding carries its fix" — which matters since no output schema exists.

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?

Purpose and the credit-saving rationale are front-loaded, and the two trailing clauses deliver the result contract compactly. The opening sentence is dense with a long list of checks, but every item earns its place by telling the agent what will be flagged.

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?

For a 7-parameter validator with a deeply nested state object and no output schema, the description covers the essentials: what is validated, the cost profile, and the shape of the result. Minor gaps remain (no explicit statement of when validation is unnecessary, no severity model), but nothing an agent needs to invoke it correctly is missing.

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 100%, so every parameter including the nested state object is already documented in the schema; baseline 3 applies. The description only lightly reinforces this, tying the tell check to the state ("a tell bigger than the state allows") and pointing to atlas_targets for target ids, without adding syntax or defaults beyond the schema.

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?

States a specific verb (check/lint) and resource (an acting paragraph or voice direction), and enumerates the exact defect classes it detects — emotion labels, mugging, lens looks, quoted speech, oversized tells, character caps. That level of specificity clearly separates it from siblings like atlas_draft or atlas_show, which generate rather than validate.

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?

"before spending credits" gives a clear trigger for when to reach for this tool, and the target parameter points to atlas_targets for valid ids. It stops short of naming an explicit alternative or stating when-not to use it, so it falls just under the top tier.

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