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

Goes well beyond the annotations by explaining the exact-versus-sampled verification behavior, the candidate status without verify, and which JSON-LD fields are user-editable versus derived. It does not elaborate on the destructive side effect implied by destructiveHint, but it does not contradict the annotations either.

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?

The description is dense but front-loaded with the core purpose in the first clause. Each subsequent clause adds necessary behavioral or contract detail. The parentheticals make it heavier than ideal, but the information is specific and earns its place.

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 complex tool with no output schema, the description covers the main return shape, editable fields, verification behavior, and points to the full docs for the caveat. It is complete enough for an agent to invoke it correctly, though the colour-refinement caveat is deferred rather than explained.

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?

The schema already documents all three parameters, so the baseline is 3. The description adds meaningful semantics around verify=true (exact proof, fallback, candidate classes) and clarifies the inline_context behavior by noting the URL resolves to the identical map. That extra context raises it to a 4.

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 action ('Discover the parameter classes of a stored model'), the resource, and the output format (JSON-LD with editable annotation slots). The purpose is clearly distinguished from the broader sibling list by focusing on classification rather than binding, calibration, or verification.

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?

Gives clear context on how to use the verify flag, including the exact automorphism proof, the sampled fallback, and the 200,000-leaf budget. It also tells the agent to read the classification docs for the caveat. It does not explicitly name alternative tools or when not to use it, so it stops short of a 5.

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