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

Annotations only declare it non-read-only, idempotent, non-destructive, and closed-world; the description adds the auth requirement (full_access API key), the role restriction with the exact error ('403 invalid_access'), and the reason a tenant might be paused. This is exactly the behavioral context annotations can't convey.

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?

Front-loaded with the action and its effect, then the permission gate, then the auth requirement and endpoint. Every sentence carries information an agent needs; 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?

For a one-parameter mutation with no output schema, the description covers the effect, auth level, role-based failure mode, and endpoint. Nothing material an agent would need before calling it is missing.

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 is a single required parameter and schema coverage is 100% — the schema already explains that `ref` is a tenant id or your own external_id. The description adds nothing about the parameter, so the baseline 3 applies.

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 ('Unpause a tenant') plus the functional effect ('Resumes sending'), so an agent knows exactly what changes. It doesn't explicitly name pause_tenant as the inverse operation, but the verb is unique enough among siblings that confusion is unlikely.

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 a concrete precondition: tenants paused by the reputation guard can only be unpaused by trusted/internal teams, and everyone else gets a 403 and should contact support. It doesn't say when to use pause_tenant vs. update_tenant or whether unpausing is safe to retry, but the key usage gate is spelled out.

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