Read the competitor watch

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

Annotations only declare readOnlyHint and destructiveHint, but the description adds critical behavior beyond that: it clearly states 'Read-only and free — it returns the stored results of past runs and never triggers a check.' It also explains the seed:true semantics, which is essential to correctly interpret results. These nuances are not present in annotations, so the description fully covers them.

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 a dense paragraph of about five sentences, but every sentence contributes necessary context (scope, state fields, seed semantics, read-only behavior, and pointer to set_competitor_watch). It is not as tight as a two-sentence version, but there is no fluff or repetition. Front-loading the core read action keeps the most important info first.

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?

The tool has a non-trivial return shape (findings plus watch state) and an ambiguity around seed:true. The description explains both the content and the seed nuance, clearly states what it does NOT do (trigger a check), and even references the web app's Ad Spy tab for orientation. Given there is no output schema, this description is sufficient for an agent to know when and how to use 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 schema already documents both parameters (limit and competitor) thoroughly. The description does not add any additional parameter-specific detail beyond what the schema provides; it only mentions the behavior generically. Thus baseline 3 is appropriate since the schema carries the semantic weight.

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 opens with a specific verb and resource: 'Read what the standing COMPETITOR WATCH has found' and details exactly what is returned (new ads plus watch state). It also distinguishes itself from siblings like set_competitor_watch by explicitly stating it never triggers a check, so an agent can tell them apart without opening schemas.

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 gives concrete use cases: 'Use it to answer "what are our competitors running that's new?", to feed a teardown, or to save something worth keeping with save_to_swipefile.' It also names the alternative for triggering a check explicitly: 'set_competitor_watch({runNow:true}) is what runs one.' This provides clear when-to-use guidance and exclusion.

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