Wait for assessment

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

Annotations already declare readOnlyHint and destructiveHint, so the description adds value by detailing polling states, timeout behavior, and exponential backoff. This goes beyond the annotations without contradicting them.

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?

Two sentences, each adding essential information. No redundancy or fluff. The critical details (polling, states, timeout, backoff, task handle) are front-loaded.

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 polling tool with two params and no output schema, the description covers key behavioral aspects like states, timeout, backoff, and the task handle pattern. It could explain how to use the task handle (e.g., 'poll tasks/get') but that is referenced succinctly.

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 50%, with only timeoutMs described. The description does not add any parameter context, leaving the required 'assessmentPid' undocumented. This is a significant gap for a tool with two 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 clearly states it polls 'air_get_assessment' until specific states (completed, failed, reportAvailable) or timeout, and returns a Task handle. This distinguishes it from sibling tools that are direct actions or retrieval, making the purpose unambiguous.

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 description mentions exponential backoff per async-jobs guidance, implying standard usage. While it doesn't explicitly state when not to use it, the context is clear that it's for waiting on assessment completion, differentiating it from synchronous alternatives like 'air_get_assessment'.

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