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

Annotations already cover read-only, idempotent, non-destructive, open-world, so the safety burden is off the description. The description instead adds the interpretive caveat that scores are relative ranks, not search volume — the single most likely source of agent misuse. It does not mention pagination or the limit-lowering behavior (that lives in the schema).

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?

Three short sentences plus a compact example, with the core capability front-loaded and the critical caveat ('not search volume') placed immediately after. Every sentence carries distinct information and nothing is padded.

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?

With an output schema, full annotation coverage and 100% schema coverage, the description only needs to add interpretation and routing. It does exactly that: it explains what the returned rankings mean and where to go for volume instead, which is the one thing structured fields cannot convey.

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%, including per-method limit caps and method enum meanings, so the baseline is 3. The description's note about method=signals largely restates the schema's own 'signals: autocomplete with click-through and shopping-intent signals', and the example JSON is illustrative rather than semantically additive.

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 resource (TikTok / TikTok Shop autocomplete and keyword ideas) and explains the signals variant adds predicted click-through and a shopping-intent flag. It is distinguishable from siblings by naming demand_find_topics as the volume tool, though it only describes 2 of the 6 methods the tool actually supports.

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 routes the agent away for one key need: 'These rank phrases; they are not search volume (use demand_find_topics for volume).' That is a real when-to-use-else signal. It does not explain when to pick method=tiktok vs shop vs trending vs ad_library, leaving that to the schema.

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