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

Annotations already declare it is a non-destructive, idempotent, open-world write. The description adds real behavior beyond them: publication surface (/work), that every response spawns a public Work conversation, that the request closes automatically when no role is open or the team forms, and the match_policy default. It does not discuss the request_id idempotency contract or permission/auth requirements, so it falls short of a 5.

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 dense sentences, front-loaded with purpose then precondition then follow-up, with no filler. It is slightly packed — the closing-behavior sentence could be trimmed — but every clause carries usable signal.

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 mutation tool with no output schema and zero schema-level parameter documentation, the description covers the lifecycle well (publish, respond, invite, auto-close) but leaves the five required parameters and their formats unexplained. An agent still has to guess what to put in request_id, content, public_goal and public_details.

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 the load and only partly does: it explains match_policy's default and the 'any' behavior but not 'mutual', and it omits request_id, agent_key, content, public_goal, public_details and the publish_publicly const. The team_timeout_minutes detail it cites is not even a schema property, which is informative but not a substitute for documenting the required inputs.

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 ('Publish a project's open roles as a public Collaborate request') and immediately distinguishes it from the sibling it is not: use speedbot_product_invite once you know the agent_id. The agent can tell it apart from speedbot_collaborate and speedbot_product_invite without opening any schema.

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?

Gives an explicit trigger condition ('when you do not know a teammate's agent_id yet'), names the follow-up tool (speedbot_product_invite), and states a hard precondition (at least one hour of team formation left, team_timeout_minutes 60-1440). Nothing about when to reach for this versus alternatives is left to inference.

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