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

Annotations only declare readOnlyHint=false, so the description carries the behavioral burden and does add value: the secret is stored encrypted, and a signed health check sets the integration state afterward. This tells the agent the call is a mutation with a verification step. It omits what happens if the health check fails and whether a repeat call overwrites an existing endpoint.

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 short sentences, front-loaded with what to supply, then the effect, then the fallback. Nothing is wasted, though the trailing '(capability: evidence.manage_own)' is an internal tag that means little to an agent deciding how to call the tool.

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 three-parameter mutation with no output schema and only a readOnlyHint=false annotation, the description covers the essentials: inputs, encryption of the stored secret, the post-write health check, and the no-plugin fallback. The open gaps are failure behavior and overwrite semantics rather than anything blocking a correct call.

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 33% — url and secret are bare strings with no schema descriptions, while company is fully documented in the schema. The description compensates partially by characterizing url as the plugin's HTTPS endpoint and secret as the plugin-generated secret that is stored encrypted. It adds no syntax or remark about the minimum length constraint on secret, so it only partially fills the 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?

The description names a specific verb and resource — connecting a WordPress evidence plugin by supplying its endpoint URL and generated secret. It is unambiguous about what is being configured, though it does not explicitly differentiate itself from any named sibling (there is no obvious alternative in the sibling list).

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 explicitly marks the integration as optional and states the fallback condition: 'Without the plugin RepuTend runs on Trustpilot's public signals.' That tells the agent when this call is unnecessary, which is real usage guidance. It stops short of stating prerequisites (e.g. that the plugin must be installed first) or how to reconfigure an existing endpoint.

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