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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, openWorldHint=true), the description discloses billing per successful call, a 7-day cache keyed on seed/country/language, a half-price cache hit, and that volume is always null so the 0-1 figure is relevance rather than search volume. That is real behavioral value not present in the structured fields; only error/permission behavior is unaddressed.

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 dense sentences: capability first, then output/cost semantics, then caching/billing. Every sentence carries distinct information with no restatement of the name or filler.

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 6-parameter, billable, open-world tool with no output schema, the description covers what comes back, how the score should be interpreted, and cost/caching behavior — the main risks for an agent. It stops short of addressing failure modes or how depth interacts with cost, but no critical gap remains.

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 already 83%, so most parameters are self-documented. The description still adds meaning beyond that: it explains the practical consequence of quote_only (price first, no run, no billing, cache hit at half quote) and clarifies that the 0-1 score is relevance from cross-source frequency and position — semantics the schema does not convey.

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 uses a specific verb ('Fan out a seed keyword') and enumerates the exact sources (autocomplete seed+a-z+question modifiers, PAA, related) plus the returned fields (source, question flag, intent, relevance score). That is far more specific than the sibling generic tools like alterlab_serp or alterlab_search, so an agent can tell what this produces without opening the schema.

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 a usable in-tool guideline: set quote_only=true to see the price before running, and note that cached repeats cost half. However, it never states when to prefer this over sibling keyword/SERP tools (alterlab_serp, alterlab_search, alterlab_ai_visibility), so cross-tool selection is left to inference.

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