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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered; the description adds the useful workflow constraint that the event identifier must come from search_events. Return values are covered by the existing output schema, so nothing critical is left undisclosed.

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?

Four short lines: purpose first, then a per-action breakdown, then the required identifier and its provenance. Every sentence carries information an agent needs and the structure mirrors the oneOf dispatch.

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 read tool with full schema coverage, complete annotations and an output schema, the description supplies exactly what structured data cannot: the action-selection logic and the upstream dependency on search_events. Nothing an agent needs to invoke 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, but the description adds meaning the schema does not spell out: which parameter combination each action demands (`poll_id` for `get`) and that omitting `status` means all statuses rather than a default. That is genuine routing value beyond the field-level descriptions.

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 states a specific verb and resource ("Read polls for the provided event") and immediately explains the action-dispatch model with the two concrete modes `list` and `get`. It is unambiguous what the tool returns conceptually, though it never names a sibling (e.g. read_surveys or create_poll) to sharpen the boundary.

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 real selection guidance inside the tool: use `list` with an optional status filter (omit to list all) and `search`, or use `get` when you already have a `poll_id`. It also states the prerequisite that `event_id` must be the UUID returned by search_events. It stops short of saying when to prefer a different tool entirely.

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