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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=true, openWorldHint=true), the description adds login requirement, the 50-item cross-activity batch limit, preview semantics (no writes at all), the irreversibility of making items PUBLIC, the fact that only updates are performed (no create/delete), and per-item error handling where failures go to a failed list without blocking others. This is unusually rich behavioral context that the annotations alone do not convey.

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?

The description is front-loaded with 【需要登录】【何时用】 and organized into bracketed sections (usage, composition chain, pitfalls), with no wasted filler on core invocation facts. It is somewhat long and includes a web-UI comparison that is helpful rationale but not strictly necessary for correct calling, keeping it just shy of perfect conciseness.

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?

Given high complexity (destructive batch mutation with confirmation workflow) and no output schema, the description compensates by covering auth, scope, sequencing, safety warnings, alternatives, and partial-failure behavior. An agent has everything needed to select and safely invoke the tool, including the two-step preview-then-commit dance.

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; the description still adds value by explaining that visibility=PUBLIC means public exposure that cannot be fully retracted once seen, and by clarifying the preview workflow (preview=true returns only before/after deltas and persists nothing). Some of this (preview behavior, cross-activity) overlaps with the schema text, so it falls short of fully independent parameter guidance.

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 states a specific verb and resource: batch-update material names and visibility across activities, up to 50 items. It also differentiates itself from the /pro web UI and from sibling tools (add_activity_material for new materials, deletion deliberately not offered). An agent immediately knows what this tool does and how it differs from relatives.

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 gives an explicit when-to-use scenario (convert handouts from registration-visible to public across several activities) and a full composition chain: list_activity_materials for ids, preview=true to see changes, confirm with user, then call again without preview to persist. Alternatives for creation (add_activity_material) and deletion (intentionally absent) are named, so the agent can route correctly.

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