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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered, but the description adds genuinely new behavior: the PDF link is time-limited (~15 minutes) and is lazily rendered on first request, requiring a retry. That is the kind of timing/latency caveat an agent cannot get from structured fields.

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?

A single dense sentence front-loads the core result, then tucks the PDF caveat into a parenthetical, and closes with the read-only signal. No sentence is wasted.

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 usefully enumerates the returned payload, which is the main thing an agent needs. The single parameter is fully documented in the schema, so the small remaining gap is mostly the absence of explicit sibling routing.

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 the schema itself explains that the identifier may be a human-typed number like 'INV-12' or an internal id. The description adds no further meaning about the parameter, 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?

The description states a concrete resource and scope: 'One invoice in full,' enumerating exactly what is returned (client, status, lines, payments, totals, PDF link). That inherently separates it from the list-family siblings, though no sibling is named and no explicit retrieval verb appears.

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?

Usage is only implied — an agent infers this is the tool for a single invoice's full detail rather than a filtered list. There is useful operational guidance about re-asking in 1-2 minutes when a PDF is being rendered, but no explicit when-to-use/when-not or named alternative.

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