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 is covered. The description adds genuinely new behavior: the async polling lifecycle (queued/running states) and an epistemic constraint that AI walkthrough output is hypothesis, not observed human behavior. That is real guidance an agent cannot get from the structured fields.

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 verb and resource, then the return contents, then two short operational sentences. The long middle clause enumerating every payload field is dense but each item carries information; only light trimming (e.g., 'what they said while trying') would be possible without losing meaning.

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 the description did not need to enumerate return contents, yet it still gives the agent the polling rule and the hypothesis caveat that the schema cannot express. The only gap is that surveyId's meaning is left implicit, but for a two-parameter read tool this is close to complete.

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 50%: walkthroughId already documents 'default the latest', and the description largely restates that default rather than adding new semantics. surveyId is undocumented in the schema and only implicitly covered by 'a usability test's findings'. Adequate but not compensating meaningfully for the coverage gap.

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 opens with a specific verb and resource ('Read a usability test's findings') and then enumerates the two result families it returns: the AI walkthrough (status, per-task success, persona sticking points, quotes, attempt steps with screenshot links) and the real participants' task results. That content inventory makes it easy to tell apart from siblings like usability_walkthrough_start (which starts a run) or synthetic_run_get (which fetches a run).

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 a concrete operational rule: 'Poll while walkthrough.status is queued or running,' which tells the agent exactly when to call repeatedly versus once. It also states the walkthroughId default ('the latest'). It stops short of naming an alternative tool or an explicit when-not-to-use condition, so it is clear but not fully routing-oriented.

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