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

Annotations only declare idempotentHint=true and destructiveHint=false; the description adds the non-obvious behavioral rule that a departed direct membership is never reactivated, which materially affects an agent's expectations and matches the idempotent 'open or reuse' framing. It also names the return payload (chat_id, created), which matters because no output schema exists, though it says nothing about auth or error conditions.

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 action, then the constraint, then the return payload — no filler. Each sentence carries distinct information the agent needs.

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 one-parameter tool with no output schema, the description covers the action, the eligibility precondition, a key negative behavior, and the return shape, which is close to complete. The remaining gap is the lack of any pointer to the alternative tool when the precondition fails.

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% and the single user_id parameter carries no description, so the description must compensate. The phrase 'with an existing active consenting shared project collaborator' does imply that user_id identifies that collaborator, but it never states the UUID form or what happens if the id refers to a non-collaborator.

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 gives a precise verb pair (open or reuse) and resource (private direct chat), plus the scope constraint that the target must be an existing active consenting shared project collaborator. This is enough for an agent to grasp the operation, but it never names adjacent siblings such as invite_direct_chat or create_conversation, so the boundary between them is left to inference.

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 precondition for use is implied — the counterpart must be an existing active consenting collaborator — which is real guidance about when this tool applies. However, there is no explicit statement of when NOT to use it or which sibling to reach for otherwise (e.g. what to do for non-collaborators), so the routing guidance is only partial.

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