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

Annotations already cover read-only/idempotent/no-destructive safety, and the description adds substantial context beyond them: the access_token is required as proof of ownership and yields nothing without it, the four status values, and that completed runs return structuredContent.result plus a presigned pdf_url that expires in 7 days.

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?

Dense but front-loaded and waste-free: the core action, the required credentials, the status enum, the return payload, and the polling cadence each appear once and in a logical order.

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?

With no separate output schema, the description carries the return-value burden and does so (structuredContent.result JSON, pdf_url with expiry). Together with the prerequisite and polling guidance, an agent has everything needed to call and interpret this tool correctly.

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 the baseline is 3, but the description adds real meaning: the access_token is not just an ID but an authorization proof the caller started the run, and the receipt_id format/provenance is clarified via the start_<bot> link.

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 specific verb and resource ('Check a run started with a start_ tool and fetch its results') and ties itself explicitly to the start_<bot> family, which cleanly separates it from siblings list_bots and validate_inventory_reorder_inputs.

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 clear usage context: call it after a start_ tool, and poll about once a minute. The prerequisite chain (receipt_id and access_token come from start_) is spelled out. No explicit when-not or named alternative retrieval tool, so it stops short of a 5.

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