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

Annotations declare write/not-destructive/not-idempotent, and the description adds genuinely new behavioral context: anonymous, unverified respondents, anyone with link can answer, publish:false saves a draft, and the share link is returned. It does not mention idempotency or failure modes, but the added context is substantive beyond the annotations.

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-loads the core action and scope, then the alternative, then question types. Dense but every sentence carries information; only the long parenthetical field lists approach bloat.

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 a 7-param nested tool with no output schema, the description covers the return value ('Returns the share link'), the anonymous/non-binding contract, draft vs publish, and question-type semantics. Gap remains around settings/timezone/closes_at, but those are documented in the schema itself.

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 57%, and the description compensates by defining question type semantics (single = pick one, multiple = checkboxes, rating 1-5, settings {scale:'nps'} = 0-10 NPS, ranking, open_text) and the publish:false draft behavior. It doesn't cover timezone/closes_at/settings fields, but the key enum-driven semantics are explained.

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 (Create) plus resource (survey) and immediately scopes it: free, anonymous, publishable or draft. It explicitly distinguishes itself from create_election_draft for binding use cases, so an agent can route between the two siblings without inspecting 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?

Explicit when-to-use and when-not-to-use: 'Surveys are for feedback, not binding votes' and 'For anything binding ... use create_election_draft.' Names the alternative tool directly, leaving nothing to inference.

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