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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so 'Reads only; changes nothing' is largely a restatement. The genuinely additive disclosure is the conditional behavior of personal links (?g=…), which return previously submitted answers under that link — a behavioral detail not captured anywhere in 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?

Three sentences, each load-bearing: what is read, the personal-link variant, and the sequencing advice. The sequencing advice is front-loaded at the point of decision rather than buried, and nothing is padded.

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?

With an output schema present the description need not enumerate return fields, yet it still names the key ones for scanning. Single required parameter, full schema coverage, safe-read annotations — nothing an agent needs to invoke this 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, but the description adds real meaning by tying the two link flavours to distinct output: a personal (?g=…) link additionally surfaces answers already given. That consequence goes beyond the schema's brief format hint.

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?

Specific verb (Reads) plus resource (a When Works For You poll) and it enumerates exactly what comes back: title, organizer, date options with yes/maybe counts, and confirmation status. This lets an agent distinguish it from get_event or get_draft without opening any schema.

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 names the downstream tool and the reason to call this first: 'Use this before respond_to_poll so you can match the person's availability to the poll's exact dates.' It also explains the branch condition for a personal link, so there is no ambiguity about when the extra data appears.

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