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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, non-destructive. Description adds that it returns status (working|completed|failed) and buyers on completion, plus polling behavior without contradicting annotations.

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?

Four sentences, no redundancy. First sentence immediately conveys core purpose. Each sentence earns its place without unnecessary detail.

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 simple polling tool with no output schema, the description sufficiently explains return values (status enum, buyers on completion) and usage pattern. References to sibling tools provide needed context.

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%, so baseline 3. Description adds value by explaining that task_id comes from find_buyers' acquisition field or a discovery job_id, and limit controls max buyers returned.

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?

Clearly states the tool polls a background buyer-discovery task, referencing specific sibling tools (find_buyers, submit_discovery_job) that create the task. The verb 'poll' and resource 'task' are distinct and 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?

Explicitly advises to use exponential backoff starting at ~20s and to stop polling once status is completed or failed. Also tells when to use: after calling find_buyers or submit_discovery_job.

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