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

Annotations only give generic hints (readOnly=false, idempotent=false, openWorld=false). The description goes well beyond them: it discloses the ~30s server wait, the polling cadence, that 'approved' returns the key exactly once and never again, what each status string means, fallback behavior on expired/invalid grants, and that the call is free and does not consume the free allowance. That is unusually rich behavioral context.

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 text is long but front-loaded and segmented into USE WHEN / HOW TO CALL / WHAT THE ANSWERS MEAN blocks, so it scans well and every sentence carries operational content. It is slightly denser than strictly necessary, which keeps it from a 5.

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?

Despite an output schema existing (so return values need not be explained), the description still maps each likely status to an agent action, gives retry timing, and covers terminal failure fallbacks. For a polling tool with tricky one-shot credential semantics, nothing needed to call it correctly is missing.

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 100% and the sole optional parameter is already documented there. The description's 'leave device_code empty to reuse the last request from this session' merely restates the schema text, adding no new syntax or format detail.

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: collect/poll the IBANforge API key once a human has approved the corresponding request. It explicitly distinguishes itself from the sibling request_api_key, which opens the request rather than collecting the result, so an agent can route between the two without opening schemas.

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?

It gives an explicit precondition ('USE WHEN: you have called request_api_key and shown the code to your human'), names the prerequisite sibling, and adds exclusions/limits such as calling once per minute, never in a tight loop, and at most one more request or poll on failure. Nothing about when to use or when to stop is left to inference.

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