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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered upstream. The description still adds genuine behavioral context beyond them: results are eventually consistent ("faces may populate while processing"), which implies an agent may need to re-poll rather than trust an empty first response.

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 sentences, zero filler. The resource and return shape come first, the workflow and consistency caveat second, which is the right ordering for an agent scanning for relevance.

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?

Single-parameter read tool with an output schema, so return-value detail is correctly omitted, and annotations cover safety. The description covers the remaining essentials: where the id comes from, what the call is for, and that results may still be populating.

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% with an example and a linked doc, so the schema already does the heavy lifting and the baseline is 3. The description earns one above baseline by tying the id's provenance to the sibling tool detect_faces, making the origin of the value actionable rather than just documented.

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?

"Returns a face-detection job's status and detected faces" gives a specific verb (returns) plus two concrete resources (job status, detected faces). It is clearly distinguishable from the sibling detect_faces (which starts the job) and from the swap tools that consume its output.

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 states the prerequisite chain explicitly: use the id from detect_faces, and use it to inspect progress before a selected-face swap. That is strong when-to-use guidance tied to a real workflow. It stops short of naming any when-not-to-use case or an alternative tool for the same result, so not a 5.

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