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

Annotations already cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=false). The description adds valuable context beyond them: the operation is asynchronous (queues a hosted job), reports progress, supports cancellation, and its result must be fetched via get_job. It lacks detail on retry/error behavior, but idempotency is already declared.

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 tight sentences with the operation front-loaded and the follow-up (get_job) placed last. No wasted wording, though it is terse to the point of omitting needed parameter context.

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?

For an async job-launch tool with no output schema, the description adequately covers the job lifecycle and result retrieval. But with 5 parameters at 40% schema coverage and no return-shape guidance, it leaves the agent under-informed about how to identify and parameterize the recipe to run.

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 40%, below the 50% threshold, so the description must compensate for the undocumented projectId, waveId, and tableIds. It mentions no parameters at all, leaving the meaning of the recipe selectors unexplained.

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: 'Compute the selected tab-book recipe.' It clearly conveys what is being produced (a tab book from a recipe with progress and cancellation), but does not distinguish itself from similar siblings such as run_table or run_analysis_plan.

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 real async-workflow guidance: 'Queues a hosted job; use get_job to retrieve its result,' which tells the agent the follow-up step. However, it offers no explicit when-to-use versus the other run_* siblings (run_table, run_analysis_plan, run_complex_survey_method).

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