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

Annotations already declare readOnlyHint=false and idempotentHint=false; the description adds real context beyond that: the append-not-replace behavior ('each call adds one document'), the input format constraint (base64 text), and the accepted file types/size. It stops short of describing failure modes (e.g. upload to a non-draft application) or rate limits, so it is strong but not complete.

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, front-loaded with the action and constraints, then the trigger condition, then the alternative-path routing. No redundancy and no filler; every clause carries an operational constraint.

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 output schema and 100% schema coverage, the description covers what an agent needs: format, size, trigger, per-call behavior, and the sibling alternative. It leaves minor gaps around what happens after upload (e.g. needing to re-check registration status) and whether duplicate documentType uploads are allowed.

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% and each of the three parameters is already documented, so the baseline of 3 applies. The description does add illustrative document examples (business register extract, articles of association, fund prospectus) that hint at which documentType values matter in practice, but it does not explain the enum values themselves beyond what the schema lists.

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 ('Uploads a supporting document for a draft LEI application') and immediately constrains scope with accepted formats and the 4 MB size cap. It is clearly distinguishable from the sibling get_upload_link, which it explicitly names as the alternative path for PDFs.

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 an explicit trigger condition ('Needed when start_lei_registration or check_registration_status says documentsNeeded') and an explicit routing rule for when NOT to use it ('for a file you can't pass exactly as text (most PDFs) use get_upload_link'). It also states the per-call semantics ('Each call adds one document'), so an agent knows whether one call is enough.

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