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

Annotations cover the safety profile (readOnly=false, idempotent=false, openWorld=true, destructive=false), and the description adds materially beyond that: partial-failure semantics with no rollback, results reported as created/failed, one notification per assignee, login requirement, and the assignee-defaults-to-self rule. This is exactly the operational context annotations cannot express.

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?

Dense, front-loaded with the 【需要登录】 prerequisite, then the scope limit, then mode semantics, then failure/notification behavior. Every clause carries operational information; nothing is padding.

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 covers the return contract (created/failed reporting), partial-failure behavior, prerequisites, and the sibling tool to call first, which is more than adequate for a 3-param batch tool. Minor gap: it does not say whether the created/failed result is per-item indexed, though this is not critical for correct invocation.

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 67%. The description adds real meaning for 'preview' (dry-run that returns a would-create/would-fail list for user confirmation) and clarifies the ≤10 bound and the assignee default, none of which is fully spelled out in the schema. goalId semantics remain unexplained, but it is self-evident from context.

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+resource+scope: '同目标批量派任务≤10' (batch-dispatch tasks under a single goal, ≤10). The '批量' + cap framing distinguishes it from the single-task sibling create_collaboration_task without naming it. Naming the sibling explicitly would have earned a 5.

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 prescribes the preview workflow explicitly (preview=true to check permissions/members and confirm, false to create one-by-one), states the login prerequisite, and routes non-members to an alternative tool (invite_collaboration_member) before assignment. It also gives a merge-prompt rule when one person gets >3 tasks, so an agent knows the when, the when-not, and the fallback.

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