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

Beyond the annotations, the description discloses key non-obvious behavior: direct chats are unique per pair and found rather than made ('created' false), agent chats are found if one exists, and project chats are never created. It also states the caller becomes administrator for group chats and that only company people are valid.

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?

The description is compact and front-loaded: it states the action, then handles each kind in turn, then closes with the project-chat exception. Every clause carries operational meaning without repetition.

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?

With no output schema, the description still discloses the important return behavior ('created' false when an existing chat is found) and covers all valid kind-specific paths plus the project-chat exclusion. An agent has enough context to choose this tool and invoke it correctly.

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 100%, so the schema already documents each parameter. The description still adds useful semantics by tying parameters to kinds and clarifying that group 'members' are besides the caller, who becomes administrator, and that direct chats are one per pair.

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 ('Open a chat') and then differentiates all three supported kinds. It distinguishes creation from lookup behavior for direct and agent chats and from project chats, which are never created here.

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 explicit conditions for each kind: 'direct' with one colleague, 'group' with title/members, 'agent' with an agent handle. It also routes the project-chat case away from this tool by naming list_chats with projectKey as the way to find it.

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