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

Goes well beyond the annotations by disclosing that no state is mutated, that the return value is a one-time intent plus a human-readable confirmation sentence, that company:write is required, and that the company is inferred from the caller rather than passed in. These are exactly the auth and side-effect details annotations cannot express.

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 tight sentences with the core purpose first, the no-side-effect constraint second, and the auth/identifier note last. No filler or restatement of the title.

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?

Explains the return payload in lieu of an output schema and covers auth and scoping, so an agent knows what to expect. The remaining gap is the required idempotency_key's role, which is neither in the schema nor the description.

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?

With 0% schema description coverage, the description must carry parameter meaning, and it names four of the five fields (display_name, website, phone, categories). It does not explain the required idempotency_key or any format/length constraints, leaving a meaningful gap.

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 and resource ('Stage a change to the merchant's own listing') and enumerates the affected fields (name, website, phone, categories), so an agent can tell it apart from the confirm_* sibling without opening either schema.

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?

'Changes nothing on its own: returns a one-time intent and a sentence describing exactly what confirming it would do' clearly establishes this as the first half of a two-step flow, implying the confirm sibling is the follow-up. It stops short of naming confirm_update_company_profile explicitly or stating exclusions.

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