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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, yet the description adds non-structured behavioral facts: it is a paid call (~$0.01), results are ephemeral until saved, and there is a recoverable setup-refusal condition. These go well beyond 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?

Three tight sentences, front-loaded with purpose then cost, persistence, and recovery guidance. Every sentence earns its place; no filler or repetition of structured fields.

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, return values need not be described. The description covers purpose, cost, persistence behavior, and failure recovery, which is everything an agent needs to invoke it 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. The description adds little param detail and its "seed topic or URL" phrasing is slightly misleading since the schema exposes only a seedKeywords array with no URL parameter, which could confuse an agent.

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 verb+resource ("Finds keyword ideas") plus the returned fields (volume, difficulty, intent) and the input shape (seed topic or URL). An agent can distinguish this from siblings like list_saved_keywords or check_keyword_audience without opening a 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?

Explicitly names the alternative for persistence ("Results are not saved until you call save_keywords") and a fallback path for failure ("call get_setup_status"). This gives clear when-to-use-this vs when-to-call-something-else routing.

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