Set the competitor watch

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

Annotations indicate readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description goes well beyond this by detailing that empty list stops the watch and clears findings, that setting is free but running spends credits, that the server trims past 5 brands, that runNow triggers an immediate background run, and that country/platform are inherited. This is rich behavioral context with no contradiction.

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 long but every sentence carries essential information: purpose, replacement semantics, credit costs, trimming, runNow behavior, inheritance, and a pointer to the related read tool. It is front-loaded with the core purpose and then details, with no fluff.

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 no output schema and two parameters, the description covers all necessary aspects: what it does, when to use, side effects (credit spending, clearing findings), constraints (max 5, domain requirement), and how to read results. Nothing essential is missing for an agent to call 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 already describes both parameters, but the description adds substantial meaning: competitors is the complete list (replacing old), empty array stops the watch, max 5 trimmed, domain is needed for Google and disambiguates Meta; runNow spends credits now and runs immediately. This goes well beyond the schema's field descriptions.

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 sets or stops a standing competitor watch — a weekly job that re-checks brands' ad libraries and reports new findings. It distinguishes this from sibling tools like list_watch_findings (for reading back) and find_competitors (one-time discovery) by emphasizing the recurring, standing nature.

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 explains when to use it (to set or stop the watch) and provides context about the weekly cadence, credit spending, and that it replaces the whole list. It points to list_watch_findings for reading results, but it does not explicitly state when to prefer a different tool (e.g., find_competitors for one-off searches) — the context is clear but exclusions are only implicit.

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