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

Goes well past the annotations by disclosing cost mechanics ($0.01/call, first 25 free, failed calls free), explaining why repeats are not free (consistent with idempotentHint=false), and describing output shaping (deduplication, engine-count ranking, question/buying-intent separation, ~200 keyword cap). The 'reads or computes only and changes nothing' line aligns with readOnlyHint=true rather than contradicting it.

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 with the core output description before cost details, and every clause carries information. It is one dense run-on paragraph, and the pricing/payment sentence is bulky relative to the rest, costing a point on structure.

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 no output schema, the description still conveys the return shape (deduplicated, ranked, question and buying-intent groups, up to 200 items) plus source engines and exclusions. Combined with 100% schema coverage and a full annotation set, an agent has everything needed to call this correctly.

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 and the schema already documents lang, country, engines, and deep. The description adds some value by explaining what deep actually produces (seed + a-z, how/what/best/vs, up to 200 keywords) and giving a seed example, but leaves lang/country/engines entirely to the schema.

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 deliverable: 'the search phrases real users type for a seed keyword' pulled from named engines, deduplicated and ranked. It also differentiates from the closest sibling (text_keyword_density) by framing output as new keyword ideas rather than density analysis of supplied text.

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?

Gives explicit use cases ('plan content, find long-tail and question keywords, or name a product') and a negative boundary ('No search volumes') that prevents misuse. It does not name a sibling alternative for adjacent needs, but the scope statement is clear enough to route correctly.

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