Close a poll

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, and the description usefully refines that by clarifying results remain readable and that re-closing is safe. It also discloses audience-display side effects (phones and the wall show live surveys or the latest closed batch) and the required scope ('Needs rooms:write'). Strong, though it does not describe failure modes if the survey_id is stale or the room code is wrong.

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 core action and the primary alternative, with no filler sentences. It is a single dense paragraph and a few clauses (the screens/wall explanation) run long, which slightly hurts scannability but each sentence carries distinct 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?

Covers the mutation's effect, what is preserved, the alternative sibling, preconditions (not a draft), idempotent behavior, the parameter source, auth scope, and the return contents ('Returns the survey, the room and its links') despite there being no output schema. Nothing an agent needs to call it correctly is missing.

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%, so the baseline is 3; the description goes beyond it by telling the agent where survey_id comes from ('Get survey_id from get_survey_results') and by framing show_results in terms of audience visibility and screen behavior. It does not, however, restate or enrich the code parameter.

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 ('Close a live poll, quiz, rating or word cloud so it stops taking answers') and immediately notes the preserved-results scope ('its results stay readable'). It also names the sibling it differs from (close_room), so an agent can distinguish it without opening schemas.

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?

Explicitly says when to call it ('once a survey has collected its answers'), how to close several ('calling it once per survey'), and the alternative for ending everything ('use close_room to end every live survey together with the room'). It even defines edge cases: re-closing an already-closed survey is allowed, a draft is not.

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