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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. Beyond that the description adds genuinely useful behavior: signed_url is a short-lived (~1 hour) link, base64 is returned only when inline is true AND the file is ≤2 MB, and every call is logged with the document id. These are real operational facts that annotations cannot express, though the ~1 hour lifetime is given only approximately.

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?

Front-loaded with purpose and return shape, then constraints, then ID provenance, then a privacy caveat — a sensible priority order. It is dense but every clause carries information; the only cost is sentence length, which makes it slightly harder to scan than a bulleted breakdown would be.

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, the description compensates by listing the exact return fields and explaining which are conditional. Access requirements, ID sourcing, size/lifetime limits, and even a compliance caveat about not echoing IBANs are all present, so an agent has everything needed to invoke it 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 would be 3, but the description adds meaning the schema lacks: the conditional relationship between inline and base64 (inline alone is insufficient — size must also be ≤2 MB) and the provenance of document_id. company_id semantics are left entirely to the schema.

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 concrete verb and resource (retrieve one document) and enumerates the returned shape {id, name, mime, size_bytes, signed_url, base64?}, plus what kinds of documents these are (receipts, invoices, booking attachments). This lets an agent distinguish it from list_unattached_documents and get_journal without opening a schema.

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?

Explains the prerequisite (connection must be granted file access) and routes the agent to the exact sources of document_id: a booking's attached_document_ids via list_bookings/get_journal, or list_unattached_documents. It stops short of an explicit 'do not use this when…' exclusion or a comparison with get_account_statement, so a 4 rather than a 5.

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