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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds meaningful behavior beyond that: the link's 15-minute lifetime, the need to re-request, output-field list, a sha256 integrity check, and handling guidance (don't paste into chat, keep links out of logs). It also enumerates the five failure modes, which is exactly the kind of context annotations cannot carry.

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 the purpose and link lifetime, then flows into parameters, return fields, and errors. Every sentence carries information, though the single dense block could be broken up for faster scanning.

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 describes the return payload (downloadUrl, downloadUrlExpiresAt, contentType, byteLength, sha256, filename suggestion) and lists all error codes. An agent has everything needed to invoke it correctly and interpret the result.

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?

Despite 0% schema description coverage, all three parameters are explained: runId identifies the run, mediaId is needed when the run has multiple files and the error lists candidates, and inline:true is conditional on png/jpeg/gif/webp under 200 KB. This fully compensates for the bare 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 — 'get a short-lived download link for a file a run produced' — with the artifact types enumerated (audio, image, video, PDF). It is clearly distinguishable from siblings like runs_evidence, inspect, or runs_get, which would not return a download URL.

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 strong operational context: download via curl/fetch within 15 minutes, call again for a new link, pass mediaId when the run has several files, and use inline:true only for small web images. It does not explicitly say when *not* to use it versus sibling tools such as runs_evidence, so it stops short of full when/when-not coverage.

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