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

The description opens with 'Read' and closes with 'Does not change model or billing', which frames this as a retrieval operation, yet the annotations declare readOnlyHint=false and destructiveHint=true. The disclaimer is scoped only to model and billing, so the actual destructive or state-mutating effect is never disclosed, leaving the agent with a misleading safety picture. That said, the description does add real context (usage/cost observations, the generation_models boundary) that annotations do not carry, so it is not a flat one-line contradiction.

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 short sentences, front-loaded with what is read and closed with the sibling-routing rule and safety disclaimer. Only 'inspection/research support' is dead weight, and the ordering (purpose → boundary → non-effect) is easy to act on.

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-value explanation is not required, and the annotations cover idempotency/open-world. But for a tool with six parameters, five required, and a heavy session-bootstrap surface, the description is thin: it never explains what work_id, arguments, or request_key mean in practice, and the destructive-hint tension is left unresolved.

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 only 50%, and the description says nothing about any of the six parameters — not work_id, arguments, request_key, or the session/version plumbing. With five required parameters and nested objects, the description needed to compensate for the uncovered half of the schema and does not; even the covered ones (read_skills, expected_catalog_version) get no clarification beyond their own schema text.

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?

Specific verb+resource: 'Read chat LLM models ... and this request's observed usage and cost reservations' tells an agent exactly what data comes back, and the final sentence carves out image/video models to a different toolset. The phrase 'inspection/research support' is vague filler that weakens an otherwise precise statement, and it doesn't distinguish itself from sibling native.get_generation_models by name.

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 does give one explicit routing rule: for image/video models and duration limits, use the generation_models toolset. But there is no positive when-to-use trigger (e.g., 'call before selecting a chat model'), and the sibling list contains native.get_generation_models and native.get_generation_defaults that are never mentioned, so an agent still has to infer which of the three to call.

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