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

The description adds real value on idempotency mechanics ('Exact client_id and body identify retries'), which goes beyond idempotentHint=true by explaining the key. However, annotations declare destructiveHint=true and the description never says what is destroyed or altered (e.g., whether an existing question or its votes are replaced), which is the most important behavior to disclose for a mutation tool.

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?

Two compact sentences, front-loaded with the create action and its shaping constraints before the exclusions. Every clause carries information; nothing is redundant with the title.

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 6-parameter mutating tool with no output schema, the definition covers creation shape, retry identity, and boundary exclusions, which is close to sufficient. The remaining gaps are the meaning of deadline and the destructive consequence flagged by annotations.

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 50%: room_id, action_id, and client_id are documented in the schema, while question, options, and deadline are not. The description adds 'distinct' to options and the 2–6 count, but says nothing about deadline semantics, and its phrase 'current action_id link' does not align with the schema's definition of action_id as an idempotency key, leaving that parameter genuinely ambiguous.

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 and resource ('Creates a room question') plus concrete shape constraints (two to six distinct options, optional action_id link). It is clearly distinguishable from siblings like propose, propose_poll_result, or open_decision, though it does not name them.

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?

The negative clause 'Does not assign roles, attest reads or grant approval' scopes what the tool is not, which is useful, but there is no positive guidance on when to use this instead of propose/open_decision/list_polls or on any prerequisites beyond the room_id OAuth note in the schema.

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