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

Adds substantial context beyond the annotations: irreversible delivery ('发出去收不回'), a 30-per-org/24h rate limit, same-content-same-day deduplication (alreadyPublished=true), and targeting semantics for MARKETING (opt-in recipients only). This goes well past readOnlyHint/destructiveHint/idempotentHint. The dedup note sits in mild tension with idempotentHint=false, but it is scoped to identical content within a day rather than a general idempotency claim, so it is not a contradiction.

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 but front-loaded and clearly sectioned with bracketed labels (auth, workflow chain, caveats), which suits the tool's complexity. It is slightly repetitive, restating the preview default that the schema already documents, which keeps it from a 5.

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?

No output schema exists, so the description carries the full burden for a 6-parameter mutation tool, and it does: auth, targeting, irreversibility, rate limit, dedup, and the preview-confirm-send pattern are all present. An agent has everything needed 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 description coverage is 100%, so baseline is 3, but the description adds meaning beyond the schema: MARKETING is delivered only to members who opted into promotion, activityId must reference a *published* activity of this same organization, and the preview=false requirement for a real send is reinforced. These are genuine operational nuances on top of the field descriptions.

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+scope: broadcast one notification to all registered org members via push + in-app inbox, and names the authority to do it (OWNER/ADMIN). An agent can immediately distinguish it from list_my_organization_notifications / mark_organization_notification_read, which are the read-side siblings.

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?

Explicitly prescribes the workflow: call with preview=true (default) to obtain recipient count, read title/body/count back to the user, then re-call verbatim with preview=false to actually send. It also states the auth condition and the narrowing rule for activity organizers (service notifications only, tied to an activity).

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