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

Annotations cover idempotency and non-destructiveness, but the description adds genuinely non-obvious behavior: per-keyword cost (~$0.004 for the audience check), that new keywords default to tracked, that track=false or exclusion suppresses tracking, and that exclusion halts tracking. This is exactly the supplementary context annotations cannot express.

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?

Two tight paragraphs, front-loaded with the core action and its bundled effects, then the cost caveat, then the error path and related tools. Every sentence carries information; only the cost parenthetical is slightly dense to parse.

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?

An output schema exists so return values need no explanation, and annotations carry the safety profile. The description supplies cost, default behavior, and failure recovery, leaving little an agent needs before invoking 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 baseline is 3, but the description adds real meaning: it explains the semantic intent of exclusion ("a keyword whose searchers aren't the buyer") and that excluding stops tracking, which clarifies the excluded/track interaction beyond the field-level text.

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 states a specific verb and resource ("Saves keywords") and enumerates the bundled side effects (tags, exclusion, rank tracking) in one call, which clearly distinguishes it from research_keywords, list_saved_keywords, and remove_keywords.

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?

It states when to use it (keywords from research or Search Console), names related tools (research_keywords, list_saved_keywords, set_up_market), and gives an explicit error-recovery route ("If this refuses because the workspace is not set up, call get_setup_status"). It falls short of a full when-not-to-use rule, but the routing guidance is strong.

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