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

The description goes far beyond the annotations. It discloses the 5-calls-per-hour shared rate limit, that credit is charged even when nothing is added, the 1 AI brain credit cost charged after work and non-refundable on failure, the requirement of an active subscription or free trial, and the asynchronous background processing (clustering/intent may be empty for a minute). Annotations only indicate readOnlyHint false and openWorldHint true, so this description carries the full burden and exceeds 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?

The description is dense but efficiently structured. It front-loads the primary purpose, then covers limits, async behavior, rate limits, costs, alternatives, and the confirm flag in a logical order. Every sentence delivers necessary information; there is no filler or redundancy, despite its length.

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 tool with significant complexity—costs, rate limits, async processing, prerequisites, and alternatives—the description covers every aspect an agent needs to invoke it correctly. It explains the confirm requirement, subscription need, charge behavior, and background processing. An output schema exists, so return-value documentation is not required. Nothing critical is missing.

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 already provides 100% coverage, with descriptions for seed_keywords ('Seed keywords to expand (1 to 20)'), confirm ('Set to true to acknowledge the AI brain credit charge...'), and website_id ('Website id from get_account...'). The description largely repeats these details and does not add new parameter-specific semantics beyond what the schema already conveys. Baseline 3 is appropriate.

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's purpose: 'Discovers new keywords from seed keywords and adds them to the website.' It specifies the verb (discovers/adds), the resource (keywords), and the mechanism (seed expansion). It also distinguishes from siblings by naming add_keywords for specific keywords and refresh_keyword_metrics for metrics, so an agent can immediately tell this tool apart.

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 explicitly tells when to use this tool versus alternatives: 'To add specific keywords as written, use add_keywords; to look up metrics of existing keywords, use refresh_keyword_metrics.' It also explains the confirm flag behavior ('without it the tool only returns the cost and your balance') and the shared rate limit with add_keywords, leaving no ambiguity about invocation context.

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