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

Discloses that provider requests are bounded and read-only, that a local commit and immutable settlement occur only when the correlation marker is present, that nothing is recorded otherwise, and that the tool never writes to the provider or retries/recreates/replays. It also states required auth scopes. This adds substantial context beyond the annotations, which only cover generic safety hints.

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?

The description is dense and front-loads purpose, conditions, and behavioral guarantees; each sentence adds a distinct constraint relevant to correct invocation. It is appropriately sized for a complex, high-stakes tool, though the single long paragraph could be more scannable with structure.

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?

Given the tool’s complexity and the absence of an output schema, the description covers purpose, behavioral guarantees, preconditions, and auth requirements well. It does not describe the return value of a successful settlement or error responses beyond refusal, leaving a minor gap for a tool this involved.

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 0% schema description coverage, the description compensates for the three optional provider-item parameters by mapping GitHub issue_number, GitLab issue_iid, and Asana task_gid to their providers and requiring exactly one. However, it does not describe the required effect_id parameter or clarify the provider enum values beyond 'the effect’s provider', leaving gaps for two of the five parameters.

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 'Settle' and resource 'one uncertain create effect', and explicitly rules out retries, recreations, and replays. It distinguishes itself from siblings by specifying the provider read and the local settlement action, making the tool's unique role clear without opening other definitions.

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?

Provides required auth scopes, a precondition (refused until deploy-owned settlement activation), an exclusion (cancelled effect with attempt_count 1 cannot be settled), and points to list_ticket_integration_effects_v2 for unconfirmed outcomes. However, the alternative guidance is somewhat indirect and does not explicitly state when to choose this tool over that read, leaving a small inference gap.

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