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

Discloses side effects (a link is created if absent, a PDF may be printed), states NOTHING IS SENT, explains the turned-off-link policy (never re-issued; invoice_share 'rotate' needs owner approval), lists CONFLICT reason codes with next_call remediation, and specifies auth (read-only/viewer FORBIDDEN) and cost (free). This goes far beyond the lone readOnlyHint annotation.

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 what the tool produces, then constraints, then refusals. Very dense with reason codes, but each clause carries substantive information; minor readability cost from cramming fallbacks and codes into one paragraph.

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 explains the return shape (ready lists parts made; missing gives reason_code, reason, next_call) plus refusal paths and auth requirements. An agent has everything needed to call it and interpret results.

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% with enums and per-parameter descriptions already in the schema. The prose adds no detail about id, purpose or language beyond what the schema states, so the baseline 3 applies.

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 (get ready / assemble) and resource (one issued invoice) and enumerates the exact outputs: document, client link, PDF, prepared message. This clearly distinguishes it from the narrow siblings invoice_pdf, invoice_message_prepare and invoice_share, which it composes in one call.

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 preconditions (only issued invoices; drafts, cancelled and written-off are refused) and implies the alternative is calling the component tools separately. It does not explicitly say when to prefer invoice_pdf or invoice_message_prepare alone, but the 'one call' framing makes the choice obvious in most cases.

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