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

No annotations exist, yet the description carries the full burden well: login required, initiator-only authorization, archiving removes the goal from default to-dos, omitted fields preserve current values, and explicit nulls clear intent/dueAt. The non-idempotency warning ('服务没有持久请求去重键') is exactly the kind of retry-safety context an agent cannot infer from the schema.

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 login prerequisite, then fields, then null/preserve semantics, then the retry hazard and verification path. Every clause carries decision-relevant information; there is no padding or repetition of the schema.

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 5-parameter mutation tool with no annotations and no output schema, the description covers authorization, field semantics, side effects of archiving, and failure/retry behavior. An agent has enough to invoke it correctly and recover safely from ambiguity.

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 only 20%, so the description must compensate, and it does: it explains the omitted-vs-null distinction for intent and dueAt and restates the status enum meaning. It does not add anything for goalId or title constraints (2–60 chars), which remain schema-only, but the highest-risk semantics are covered.

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+resource (update a collaboration goal) and enumerates the mutable fields (title, intent, dueAt, status with its three enum values), plus the actor constraint ('发起人' / initiator). It does not, however, differentiate itself from close_collaboration_goal, which plausibly overlaps with setting status=COMPLETED/ARCHIVED — the agent must guess which one to call for closure.

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 operational guidance: query get_collaboration_goal to verify, and do not blindly resend after a timeout because there is no persistent request dedup key. It stops short of naming when to prefer this over close_collaboration_goal, leaving the main sibling ambiguity unresolved.

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