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

Annotations declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, and the description adds genuinely useful context beyond them: the draft expires 24 hours after creation and the agent must not describe the poll as published. It does not discuss permissions, rate limits, or what happens when a draft expires mid-edit, so it is not exhaustive for a write tool.

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?

Three sentences, front-loaded with the operation and its constraints, followed by the return shape and the critical handoff instruction. No filler, and the prohibition on announcing publication is placed last where it lands hardest.

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 listing id, token, version and edit_url is mild redundancy, but the expiry window and the publish-handoff rule are the details an agent would otherwise get wrong. Together with the fully documented schema and annotations, the definition is sufficient to call the tool 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 description coverage is 100%, so the schema already documents title, questions, email_mode, email_purpose and the nested image_url fields with character limits and defaults. The description only restates the question/option count bounds already present in the schema, adding no new semantics. Baseline 3 is appropriate.

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+resource ('Create a poll draft') and immediately bounds the shape (1-100 single-choice questions, 2-10 options each). This is unmistakably distinct from the sibling get_poll_draft and update_poll_draft, which read and modify drafts rather than create them.

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 concrete post-call workflow guidance: hand the edit_url to the person so they can review, verify and publish it in the browser, and never claim the poll is published. It stops short of explicitly naming update_poll_draft as the path for later edits, so the alternative selection is implied rather than stated.

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