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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile needs no restating. The description adds one genuinely non-obvious behavioral note — that observed state transitions do not imply immediate agent change — which manages expectations in a way annotations cannot. It stops short of saying whether state is polled, final, or how stale it may be.

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 with the purpose front-loaded and the caveat trailing as a qualifier. No filler or repetition, though 'Follow' is a slightly imprecise verb choice where 'Get' or 'Check' would be sharper.

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?

An output schema exists, so return values need no explanation, and the tool is a simple one-parameter read. Still, the definition leaves both the parameter contract and the call context (when, how often, and after what) to inference, which is a noticeable gap even for a low-complexity tool.

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 description coverage is 0% and the single parameter feedback_id has no description in the schema. The description gestures at provenance ('your submitted agent feedback'), which implies the ID comes from submit_agent_feedback, but it never says what form the ID takes, whether it must be one you own, or what happens with an invalid ID. With low coverage the description should compensate and largely does not, though the name itself carries most of the meaning.

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 names a specific resource (the recorded processing/application state of submitted agent feedback) and implies the natural pairing with the submit_agent_feedback sibling. The verb 'Follow' is softer than 'Get' or 'Retrieve', but the object of the lookup is unambiguous enough that an agent can tell this apart from submit_agent_feedback or get_task_status.

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?

Usage is only implied: 'your submitted agent feedback' signals this is called after submit_agent_feedback, but the description never states that sequencing explicitly or names any alternative. There is no when-not guidance, so an agent must infer that this is a post-submission polling tool rather than a general status endpoint.

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