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

Far exceeds the annotation baseline (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) by disclosing login requirement, an async background read of 10–60s, and critically that returning does not mean processing is complete. It also states materials are data-only, extracted values must be evidence-grounded, and images require user verification — rich behavioral context not present in structured fields.

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?

Front-loaded and information-dense: login gate, action, timing caveat, and parameter rule all arrive early. The arrow/semicolon compression is efficient, though the terse notation borders on needing decoding and could be marginally clearer at the same length.

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 an 8-param tool with nested objects and no output schema, the description covers the gaps that matter: auth requirement, async timing, the exclusivity rule, and what the return value does not guarantee. The data-handling caveat about verification adds needed context. Only the absence of explicit when-not-to-use guidance keeps it from a 5.

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?

With 100% schema coverage the baseline is 3, but the description adds a real constraint the schema does not express: only one of the material variants may be provided at a time. The size/count limits it repeats are already in the schema, so the incremental value is the exclusivity rule rather than the limits.

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 with the compressed notation 活动材料→新草稿 (activity material → new draft), naming the input and the produced artifact. It also distinguishes itself from siblings by naming the downstream workflow (get_activity_draft→update_activity_draft→publish_activity_draft). The arrow shorthand is slightly terse but the purpose is unambiguous.

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 tells the agent to supply exactly one of text/url/fileRef/fileBase64/image/fromActivity — a genuine usage constraint. It also locates the tool in a workflow chain, clarifying what comes before and after. No when-not-to-use exclusion is given, so it falls short of a 5.

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