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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), but the description adds real behavioral context not present there: the 4 MB size ceiling, the accepted MIME types (PDF/JPG/PNG), the base64 encoding requirement, and an anti-fabrication guardrail that the POA must be one the user actually gave as signed.

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?

Three sentences, each earning its place, with the core action and payload described first and the routing rule and precondition following. No filler or restatement of the title.

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 write tool with no output schema, the description covers format, size, encoding, the fallback path, and the trust precondition. It does not say what happens if a POA was already uploaded (the idempotentHint implies replacement) or whether the application must be in a particular draft state, which are the only meaningful gaps.

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 meaning beyond the schema for 'content': the 4 MB ceiling and the accepted formats, which are not stated in the property description ('base64-encoded'). It does not add anything for leiId, which the schema already sources from start_lei_registration/list_my_leis.

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 (uploads) plus the exact resource (the hand-signed limited POA for a draft LEI application) and the transport form (base64 text). It is clearly distinguishable from the sibling upload_signed_transfer_poa and from get_upload_link, which it names directly.

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 explicit when-to-use ('files small enough to pass exactly as text'), when-not ('for anything else (most PDFs)'), the named alternative with the argument to pass (get_upload_link with document 'limited_poa'), and a precondition ('Only upload a POA the user gave you as signed'). Nothing 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.