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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior. The description adds the crucial non-obvious trait beyond that: download links are valid for only one hour, plus the operational consequence (re-call for fresh links). That is exactly the kind of time-bound behavior an agent would otherwise miss.

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?

Two short sentences, front-loaded with what the tool returns and its expiry constraint, ending with the action instruction. No filler or repetition of the title.

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?

Complete for a simple two-parameter read tool with annotations covering safety and a full schema. The one-hour expiry and refresh guidance cover the main operational risk; only minor gaps remain, such as whether expired links are omitted or returned broken, and there is no output schema to compensate.

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 both parameters are documented in the schema, including the include_data default and meaning. The description adds the notion that returned items are downloadable artifacts, but does not clarify run_id accepting a request id or elaborate on include_data. Baseline 3 applies since the schema carries the parameter detail.

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 and resource ("The files a workflow or agent run made") with concrete examples (reports, spreadsheets, images) and scope tied to a run_id. It is clearly distinguishable from siblings like get_run or list_runs, which return run metadata rather than artifacts.

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 actionable usage instructions: hand the links to the person, and call again for fresh ones because links expire. It does not name an alternative tool or state when not to use it, but the invocation context is clear.

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