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

Beyond the readOnly/openWorld annotations, the description discloses non-obvious runtime behavior: the download URL expires after 15 minutes, the file is generated lazily on first fetch and may take up to a minute for a presentation, and an X-Missing-Pictures response header counts unreachable pictures. These are exactly the operational details an agent cannot infer from annotations or schema.

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?

The core purpose and format mapping are front-loaded, followed by timing and error-header details, so the paragraph reads in priority order. It is dense and parenthetical in places ('full size; zip_small to attach to a mail'), but nearly every clause carries information an agent needs.

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 three simple parameters, no output schema, and no nesting, the definition covers everything needed: what is produced, how to choose a format, what the return value is (a URL), its lifetime, its latency, and the partial-failure signal. Nothing an agent needs to invoke it correctly is missing.

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 already 100%, so the schema documents each field. The description still adds real meaning by mapping formats to resource types (pptx/pdf for a presentation, zip for storyboard frames) and clarifying the default behavior when format is omitted, plus the constraint that slide_id pairs with png output.

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 the resource precisely — a downloadable file of a doc, presentation, or storyboard — and enumerates the concrete output formats per resource type (pdf/docx, pptx/pdf, zip/zip_small, png). It implicitly separates this from read_doc by framing export as producing a file to 'download and attach', though the leading verb is nominalized rather than stated outright.

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?

It gives clear situational guidance: zip_small when attaching to a mail, and 'to see how a presentation is drawn, read its pdf, or one slide as png with slide_id' as the alternative path. It does not explicitly say when to prefer read_doc over export for content inspection, so the routing guidance is contextual rather than exhaustive.

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