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

Adds substantial context beyond annotations: the two-party confirmation semantics, the authorDone/claimerDone state fields, and precise non-retry conditions for 403/409. Neither the annotations nor schema convey any of this.

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?

Front-loaded with the auth tag and core gating rule, then error codes, then the chain. Dense but every clause carries actionable meaning; slight compactness in the chain notation costs a little readability.

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 non-idempotent mutation with no output schema, the description covers auth requirement, prerequisite (claimed session), error semantics, and the surrounding workflow — everything an agent needs to invoke it safely.

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% and the schema already documents both parameters (needId, conversationId, including that conversationId comes from contact_need). The description adds no per-parameter detail, which is the correct baseline 3 at full coverage.

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 (confirm completion) targeting the caller's own claimed session, and distinguishes from cancel_need/reopen_need by describing the mutual two-party completion mechanism (authorDone/claimerDone).

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?

Explicit when-to-use (only one's own claimed session, confirm facts first), explicit error handling guidance (403 non-participant, 409 no claim/already done/need closed — do not retry), and an explicit combination chain get_conversation_needs→confirm→complete_need.

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