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

Goes well past the annotations: discloses output format and approximate dimensions, default-page behavior, that an out-of-range page is rejected with the page count, the DRAFT watermark on drafts, and per-account rate limiting with a wait time returned on rejection. The read-only claim is consistent with readOnlyHint rather than a restatement of it, since it specifies nothing is stored or sent.

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-loads what the tool returns and what it is not, then layers usage, edge behavior, quality caveat, and rate limiting. Every sentence carries information, though the read-only sentence is largely redundant with readOnlyHint and the whole is near the upper bound of useful length.

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 two-parameter, no-output-schema, read-only preview tool, the description covers return medium, sizing, defaults, error behavior, draft watermarking, fidelity limits, and rate limiting. An agent has everything needed to call it correctly and to know when not to.

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 baseline is 3, and the description earns above that by adding runtime semantics the schema cannot express: page defaults to the first page, and a page past the end is rejected and the page count is returned (useful because 'page' is capped at 500 in the schema, not at the real count). It does not describe the id format, but the schema already labels it.

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+resource (returns one page of an invoice as a JPEG image) and immediately names its distinguishing scope: it is a rendered page, not the document. It explicitly separates itself from get_invoice_pdf (the file to save) and get_invoice (the exact values), so an agent can route without opening sibling schemas.

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 the use case ('look at how an invoice or a draft is laid out'), the alternative for saving/passing on (get_invoice_pdf), and the alternative for exact values (get_invoice). The trade-off driving the choice — reduced image, small print hard to read — is spelled out rather than implied.

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