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

The sole annotation only asserts destructiveHint=false, so the description carries most of the behavioral burden and does so thoroughly: it warns the send is irreversible ("不可撤"), documents same-day same-content idempotency and a rate cap of 30 per organization per 24h, and discloses the consent requirement for MARKETING. These are exactly the traits an agent could not infer from the schema. Irreversibility is disclosed rather than contradicted; sending is additive, so destructiveHint=false is not in direct conflict.

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?

Highly dense but front-loaded: the bracketed permission gate comes first, then action, then the preview workflow, then constraints. Every clause earns its place, though the telegraphic Chinese packing of idempotency and rate limits into one final clause is harder to parse than a short bulleted flow would be.

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 6-parameter mutating broadcast tool with no output schema, the definition covers the essentials: authorization, irreversibility, the dry-run-to-send transition, targeting rules, and quota limits. An agent has everything needed to invoke it safely and correctly.

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 100%, so the baseline is 3, but the description adds real meaning on top: the preview workflow (default counts recipients without persisting; true send requires explicit false), the consent semantics behind kind=MARKETING, and the constraint that activityId must reference a published activity of this organization. Only the length limits remain schema-only.

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 names a specific verb and channel scope — "群发推送及收件箱" (bulk send into push and inbox) — on the organization resource, and it implicitly separates this from sibling tools such as send_message and mark_organization_notification_read by being an organization-wide broadcast. An agent can tell what the tool does without opening the schema.

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 states exactly when the tool applies and who may use it (requires login, OWNER/ADMIN only; activity organizers restricted to activity service notifications), and prescribes the correct call sequence: default preview to obtain headcount, then preview=false once title/body/headcount are confirmed. It also routes kind selection (SERVICE vs MARKETING-only-to-opted-in) and constrains activityId to a published activity of this org.

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