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

Annotations only supply destructiveHint=false, so the description carries the burden and does so richly: 5-minute PUT lifetime, host uploading local bytes with the same MCP credentials and no public link, immediate publish upon HTTP success, broadcast into the activity group, and PUBLIC vs REGISTERED visibility semantics. The explicit 'prepare ≠ published' warning discloses a failure mode the agent would otherwise get wrong.

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?

Every clause carries information — auth scope, workflow, upload mechanics, publish side effects, and a caveat — and the default and prerequisite are front-loaded. The semicolon-chained single block is dense and somewhat hard to scan, but there is no filler text.

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 mutation tool with 9 params, no output schema, and partial schema coverage, the description covers the workflow, the non-obvious publish side effect, visibility rules, and the state-transition caveat. Minor residual gaps: what the tool returns in preview mode (hash field name, PUT URL shape) and any rate/retry limits are not stated.

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 33%, but the description compensates for the most consequential gaps: it explains the preview/previewHash pairing (previewHash is undocumented in the schema), the default of preview, and what PUBLIC vs REGISTERED visibility actually means downstream. activityRef, fileName, kind, and mime still receive no added meaning, so it is not a full compensation.

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 conveys a specific verb+resource: obtain a short-lived PUT address to upload organizer material (slides/file/photo) to an activity. It is clearly not a generic 'add material' tool, since it describes the two-phase prepare-then-commit flow. It loses a point because the leading token '登录/主办方·对外' is a scope/permission marker rather than a purpose statement, and no sibling (prepare_activity_photo_upload, add_activity_material) is named for contrast.

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?

Strong internal guidance: it states the default preview=true, that the agent must display activity/fileName/size/visibility and get confirmation, then re-call with identical params plus previewHash and preview=false. It also warns explicitly that 'prepare is not publish success, do not fabricate uploaded' — a real anti-hallucination guardrail. It lacks any explicit comparison to the sibling upload/material tools, which keeps it at 4 rather than 5.

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