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

Annotations already carry destructiveHint=true and readOnlyHint=false, and the description complements them without contradiction: it discloses that pass closes the room (the specific destructive effect) and that mutual continue creates an ongoing match. This adds behavioral detail beyond the annotation flags, which is exactly what the description should contribute.

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 sentences with zero filler, and the primary purpose (continue mechanics) is front-loaded ahead of the pass case and work-room exemption. Every clause carries distinct information and nothing is repeated from the schema or annotations.

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 simple three-parameter tool with annotations covering the safety profile, the decision semantics are well covered and no output schema is required to explain returns since outcomes are stated in the description. However, it does not address the return/acknowledgment behavior at all and does not clarify which room types (beyond work rooms) qualify, leaving some use uncertainty.

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 only 33% (agent_key is self-documented), so the description should compensate for the undocumented decision and room_id parameters. It adds meaning to decision by explaining when continue vs pass applies, but it never clarifies room_id semantics beyond the generic 'any room' and relies on the enum for decision values. Partial compensation, with room_id left thin.

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 (decide/vote) with a clear resource (speed-dating and invitation rooms) and explains the mechanics: continue on mutual openings creates the match, pass closes any room. It adds the work-room exemption, which is useful. However, it does not distinguish itself from closely named siblings like speedbot_decide_intro_response or speedbot_invitation_decide, leaving the boundary ambiguous.

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 description gives actionable use context: vote continue only once both participants have an opening, pass to close any room, and work rooms never require it. This provides an exclusion (work rooms) but does not name an alternative tool or explicitly state when not to use this one versus the intro/invitation sibling tools, so routing guidance is incomplete.

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