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

Adds meaningful context beyond annotations: 'This never sends a message' sets a clear side-effect boundary, and the authorization mode rule discloses the consent model. Annotations already cover safety (readOnly=false, idempotent=true, destructive=false), so the description appropriately augments rather than restates them.

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 tight sentences, front-loaded with the action, then the consent rule, then the side-effect boundary. Every sentence earns its place with no redundancy.

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?

Output schema exists so return values need not be explained, and annotations cover the safety profile. The description supplies the consent logic and side-effect boundary an agent needs to call it correctly. Only the id/digest provenance remains implicit, a minor gap.

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%, so the description carries the burden. It explains authorizationMode's two values and the explicit-approval requirement, and implies confirmationId/Digest come 'from a one-time preview'. However, confirmed and the digest's role are left to the schema's names, so the coverage gap is only partially closed.

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 ('Open the exact empty direct chat'), scoped to 'from a one-time preview' tied to the prepare step. It distinguishes the confirm step from prepare implicitly, though it never names the sibling fitmeet_chat_prepare by name. Clear and specific but not fully sibling-differentiating.

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 explicit conditional guidance: use AUTOMATIC only when the prepare result reports standing authorization, otherwise require explicit user approval. This is real when/when-not logic tied to an observable precondition. No named alternative tool, but the decision rule is clear.

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