suggest_keywords

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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds useful behavioral context beyond that: the tool returns specific metrics and requires geo/language targeting for volume relevance, helping the agent understand output expectations and input sensitivity.

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 two sentences with no filler. The main action and output are front-loaded, and the second sentence adds a necessary input prerequisite. Every sentence earns its place.

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 present and readOnly/openWorld annotations, the description covers the core inputs, output metrics, and a key prerequisite. Minor gaps like the effect of limit and include_search_partners are optional and have defaults, so the description is sufficiently complete for correct invocation in most cases.

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 0%, so the description must compensate. It does map 'seed terms and/or a URL' to seed_keywords and seed_url, and 'geo and language IDs' to geo_target_ids and language_id. However, it leaves limit, include_search_partners, and customer_id semantically unexplained, and slightly overstates language_id as required when it actually has a default.

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 and resource: 'Generate keyword ideas from seed terms and/or a URL,' and specifies the returned metrics (search volume, competition, bid range). This clearly differentiates the tool from siblings like keyword_performance and keyword_volumes, which focus on existing keywords rather than generating new ideas.

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 implies when to use the tool: when keyword ideas are needed from seed terms or a URL. It also provides a prerequisite (geo and language IDs for relevant volumes), but it does not explicitly state when not to use it or name alternatives such as keyword_volumes for known keywords.

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