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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is carried by structured data. The description adds useful behavior about the parent/child linkage and about empty options producing a discussion. It says nothing about what requestId does for idempotency, what side effects (notifications to participants) creation triggers, or what the destructiveHint means in this context, leaving real gaps.

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 short sentences, front-loaded with the core capability before the workflow detail. Nothing is redundant. It is slightly compressed to the point of being telegraphic ('kind city', 'parentId pointing to'), which costs a little readability.

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?

This is a mutation tool with 8 parameters, zero schema description coverage, and no output schema, so the description is the only source of semantics. It covers the question-creation workflow but leaves the identity/plumbing parameters (eventId, participantId, requestId) and the idempotency behavior completely unexplained — an agent cannot confidently construct a valid call without external knowledge.

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 0% across 8 parameters, so the description must carry all semantic weight. It explains only three things: kind values city/restaurant, parentId's role, and the empty-options convention. eventId, participantId, requestId, agent, and title — including four required parameters — are never characterized, so an agent must guess their meaning from names alone.

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 and resource pair: 'Ask a question or create a poll.' That distinguishes it from siblings such as add_poll_option, vote, and decide_question, which operate on an existing question rather than creating one. It does not explicitly name those siblings as alternatives, keeping it just 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?

It gives concrete sequencing guidance — 'Use kind city first, then restaurant with parentId pointing to the city question' — which tells the agent how to chain calls for the two-phase flow. It also states the empty-options case means an open discussion. There are no explicit when-not-to-use conditions or named alternative tools, but the context is clear.

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