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

Annotations already cover the safety profile (writes, non-idempotent, non-destructive, open-world), so the description's added value is the return contract: a decision with a shareable `url` plus a private `admin_token` and `manage_url`. Flagging the token as something to 'keep private' is meaningful operational context. It does not discuss auth requirements, rate limits, or what happens on inference failure, so it stops short of a 5.

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 one-line purpose, then organized into the easy path, the exact-control path, the availability caveat, and the return values. Every sentence carries distinct information; the examples are compact and each demonstrates a different `type`.

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 six parameters, zero required, and no output schema, the description supplies exactly the missing pieces: which parameter combinations are valid, the type-inference behavior, and the shape of the return value including the sensitive admin token. An agent has everything needed to call this correctly on the first attempt.

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?

Adds substantial semantics beyond the 83%-covered schema: how `text` triggers type/option inference with four worked examples, the cardinality rules per type (2-5 poll options, 2-12 ranking options), that `question` alone yields a check-in, that availability requires `text`, and that `timezone` governs relative words like 'tomorrow'. These are cross-parameter interaction rules the schema cannot express.

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 concrete verb (create) plus the exact resource variants (poll, check-in, availability board, ranking) and the outcome (a shareable link). The creation operation is unambiguous against the lifecycle siblings close/delete/get/reopen/respond, and the subtype enumeration tells an agent exactly what can be produced.

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 routes between two invocation modes: 'Easiest: pass `text`' with worked examples per type, versus 'For exact control, pass `question` plus `options`'. It also states a hard constraint ('Availability must be created from `text`') and a prerequisite (timezone needed for correct local slots), 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.