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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The word 'soft-delete' is the one piece of added value — it tells the agent data is retained rather than purged — but the description never says whether the poll can be restored, whether it disappears from read_polls, or what happens to attached questions/results.

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?

One short sentence, front-loaded with the operation and its key modifier. Nothing is wasted and nothing is buried.

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 and annotations cover safety and idempotency, so much of the burden is off the description. Still, for a destructive mutation the description omits recovery semantics and post-delete visibility, which are the questions an agent actually needs answered before calling it.

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 poll_id and event_id are fully documented in the schema itself. The phrase 'for the provided event' reinforces event scoping but adds no format, constraint, or lookup guidance beyond what the schema already supplies; baseline 3 applies.

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+resource ('Soft-delete a poll') and adds a qualifier ('soft') that materially shapes what the operation is. It does not explicitly distinguish itself from close_poll, reopen_poll, or publish_poll in the sibling set, so it falls short of a 5.

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?

There is no statement of when to delete versus when to close_poll or reopen_poll, both of which appear in the sibling list and represent plausible alternative intents. The agent is left to infer that 'delete' means permanent removal from active use rather than a state change.

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