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

Annotations only supply the destructive/idempotent/openWorld profile; the description adds the failure mode (409), the precondition that even hidden questions block removal, the restriction to user-added sections, and the return value. Those are real behavioral facts an agent cannot get from the structured fields.

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, zero filler, front-loaded with the action and its precondition before the error case and return value. Every sentence contributes a distinct fact.

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 destructive mutation with no output schema, the description covers preconditions, refusal behavior, and the returned payload, and the annotations cover safety. Nothing an agent needs before invoking 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?

Schema coverage is 100% and both parameters are fully documented in the schema (including a format example for section_key), so the description adds no additional parameter meaning. Baseline 3 applies when the schema carries the load.

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 precise verb and resource ('Remove a section ... to this automation's Policy') and narrows scope to sections 'a person added', which separates it from addConfigSection/renameConfigSection/listConfigSections in the sibling set. An agent can identify the target object and its provenance without opening the 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?

Gives an explicit precondition ('once it holds no question, hidden ones included') and the exact refusal conditions (questions present, or module-template section → 409). It does not name an alternative tool or a cleanup path for refused cases, but the when/when-not guidance is unusually concrete.

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