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

Annotations already carry destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuinely new context beyond the annotations: 'Resets its result and retains history' tells the agent what state changes, and the scope caveat prevents a false expectation of tool creation or access grants.

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 that each earn their place: the action and scope, the side effect on prior results, then the exclusion. Front-loaded with the operation before the caveats.

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 and a nested definition object carrying seven required subfields, the description supplies the missing behavioral essence (reset and history retention) that annotations alone do not. What remains, the shape of definition and version handling, is adequately covered by the schema.

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 schema coverage at 57% and a seven-parameter call including a nested definition object, the description only maps 'with a reason' to the notes field and implies capability naming for custom_ entries. The remaining parameters, including expected_version and idempotency_key, are left entirely to the schema, so this is a baseline adequate score rather than compensated coverage.

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 states a specific verb and resource: editing a capability expectation or adding a business-specific custom_ capability. It distinguishes the custom_ case from ordinary edits but never explicitly names the read-only siblings (capability_checks_get, list, report, test) it is not, so an agent must infer the boundary rather than being routed to it.

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?

The 'with a reason' phrasing signals the notes requirement, and 'Does not create a provider tool or grant execution access' is an explicit exclusion against adjacent capabilities. However, no alternative tool is named for the cases it excludes, so guidance is clear but not fully directive.

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