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

Annotations only declare readOnlyHint=true; the description goes further by disclosing the response contents (role and account status) and the key-scoped access model, which is real behavioral context. It does not mention ordering, pagination, or what an empty result means, but for a zero-parameter read that is a minor omission.

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 compact sentences, front-loaded with what the tool returns before the cross-tool convention note. The middle sentence is slightly tangential to this tool's own invocation but earns its place as orientation for downstream calls. The trailing capability tag is boilerplate but harmless.

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 no parameters, no output schema, and a read-only annotation, the description covers what the agent needs: what comes back and how the key scopes it. The only gap is the exact record shape (name, id, domain fields) and whether multiple companies change the result size.

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?

There are no input parameters, so the baseline is 4. The description adds orientation value by explaining the downstream convention — company plus Trustpilot domain when the key reaches multiple companies, versus case_id for case-scoped tools — which helps the agent use the output correctly.

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 names the resource and its contents precisely: the companies the caller's key reaches, plus role (owner or member) and account status. It is distinguishable from every sibling, which all operate on cases, reviews, or filings. It stops short of an explicit verb like 'list', relying on the tool name to carry that.

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?

Usage is only implied: an agent must infer 'call this to discover which companies your key can act on.' The second sentence is genuinely useful routing guidance, but it explains how other tools accept a company identifier rather than when to call this one. No exclusions or alternatives are stated.

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