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

Annotations already indicate readOnlyHint and openWorldHint, and the description adds valuable behavioral context beyond them: results include from_cache/stale flags, the remaining-lookups balance, and the fact that lookups may be consumed. This helps the agent anticipate cost and data freshness without contradicting the annotations.

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 compact and front-loaded with the core purpose, followed by parameter notes and behavioral caveats. Each sentence adds useful information, though the parenthetical '(may use lookups)' and the word 'honest' add slight stylistic clutter without major harm.

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?

The description covers the required parameters, modal variants, source restriction, project_id provenance, caching flags, and lookup consumption. An output schema exists, so return-value details are not required. The main missing context is a brief explanation of what each mode conceptually returns and the meaning of language_code/location_code, but defaults and names largely compensate.

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?

The input schema has 0% description coverage, so the description must compensate. It clarifies mode, term, source, and project_id meaningfully, but it leaves limit, language_code, and location_code to rely on their names and schema defaults. This is partial compensation rather than complete parameter documentation.

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 clearly states the tool performs keyword research and lists the modes (overview, ideas, suggestions, related) and output metrics (volume, difficulty, intent, CPC, opportunity score). This distinguishes it from ranking-focused siblings like get_keyword_rankings, though it does not explicitly name an alternative.

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?

The description gives useful within-tool constraints, such as source being valid only for overview and suggestions and project_id being optional for overlaying tracked keywords. However, it provides no guidance on when to choose this tool over related siblings like get_keyword_rankings or analyze_competitor_domain.

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