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

Beyond the annotations (readOnly=false, openWorld=true, destructive=false), it discloses auth/role requirements, irreversibility (不可撤), channel scope, the preview workflow, and a 24h per-organization rate limit of 30 – unusually rich behavioral context. The one caveat is the '同日同文幂等' claim, which sits in mild tension with idempotentHint=false, though the scoping to same-day/same-content keeps this from being a hard 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?

It is dense but front-loaded, opening with the critical auth/role constraint in brackets and packing the workflow, kind semantics, and limits into a compact block with no filler. The semicolon-chained clauses are efficient though slightly heavy to parse in one pass.

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 complex, non-reversible bulk-mutation tool with no output schema, the description covers who may call it, the preview-then-confirm workflow, constraints, and rate limits. The only gap is the shape of the actual send response (only the preview's count is mentioned), but everything needed to call it correctly is present.

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%, so the baseline is 3, but the description adds real meaning beyond the schema: activityId must reference a *published* activity of the organization, and MARKETING is restricted to users who opted into promotion. preview/kind semantics largely restate the schema, so it is a modest but genuine value-add.

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 gives a specific verb and resource: bulk-send (群发推送) plus inbox delivery of an organization notification, and it is clearly distinct from siblings such as list_my_organization_notifications or mark_organization_notification_read. An agent can identify exactly what the tool does and that it is the send variant.

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 strong usage conditions: login plus OWNER/ADMIN required, activity organizers limited to activity-service notifications, SERVICE vs MARKETING targeting, and preview-before-send. It does not name an explicit alternative tool, so it falls short of a 5, but the when/when-not context is clear.

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