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

Annotations already mark this as a write operation with open world implications, but the description goes further by disclosing that each run spends leads (one per result), which is a critical side effect. It also reveals nuances like 'Close also needs one manual export first to save its field mapping' and that 'csv' | 'xlsx' | 'json' require no setup, adding substantial behavioral context 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?

The description is three sentences long and front-loaded with the primary purpose. It packs in essential warnings and limitations without excessive fluff, though the capitalized warning sentence ('IT SPENDS LEADS ON EVERY RUN...') may be slightly jarring but effectively emphasizes the risk. Each 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?

For a creation tool with an output schema, the description covers all major aspects: what the tool does, cost implications, integration requirements, and limits. It does not need to explain return values because the output schema exists. The inclusion of the 20-automation limit and 25-cities-per-run cap adds important context that would otherwise be 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?

Schema coverage is 100%, so parameters are already documented. The description adds extra meaning by clarifying that cities can be passed as plain strings and are resolved automatically, and by explaining that certain destinations require existing integrations while others do not. This goes beyond the schema's basic descriptions, though it does not cover every parameter in equal depth.

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 starts with 'Create an automation: re-run a search on a schedule and send the results somewhere automatically,' which uses a specific verb (create) and resource (automation) and explains the core functionality clearly. It distinguishes from sibling tools like delete_automation, update_automation, and list_automations by focusing exclusively on creation.

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 provides clear context on when to use this tool: it creates scheduled recurring searches and requires user confirmation due to lead spending. It also mentions integration prerequisites and limits (up to 20 automations). However, it does not explicitly name alternatives (e.g., update_automation for modifying existing automations), so it stops short of a 5.

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