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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=false, so the mutation profile is covered structurally. The description adds useful operational context ('never include secrets,' 'Not launch approval,' decisions are client-reported), but it never explains what a destructive write replaces or how revision conflicts are handled.

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?

Four short, front-loaded sentences with no filler; the primary action leads and constraints follow. The telegraphic style occasionally costs clarity, but every sentence carries information.

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 annotations cover the safety profile. Still, for a destructive, revision-sensitive state write with low schema description coverage, the description omits conflict/replacement semantics that an agent needs to call it correctly.

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 only 33%, so the description must compensate, and it partially does: 'pending wording,' 'user-supplied/delegated,' and 'proposals' map onto the proposed/supplied/delegated/proposed status values, and it names surveyChoice=no_questions. It says nothing about blockId, proposalRevision, or the ignored expectedRevision, leaving meaningful gaps.

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 describes an action ('record pending wording or user-supplied/delegated decisions') but never names the resource as test construction state, leaving the agent to infer it from the title and the `construction` array. It does hint at scope via 'Not launch approval,' but does not cleanly separate itself from siblings like set_survey or update_test_block.

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 one concrete conditional ('Set surveyChoice=no_questions when requested') and one exclusion ('Not launch approval'), plus a pointer to update_test_block for matching proposals. However, it never states when to call this instead of set_survey, set_test_audience, or update_test_block, so routing remains partly inferred.

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