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

With no annotations, the description carries the full burden and does disclose meaningful traits: it is a notification trigger with defined change conditions, it has a 3-website limit, and it persists 'the address and your agent name'. That storage disclosure is valuable privacy context an agent would not otherwise get. It omits what happens at the limit, whether re-watching the same URL duplicates, and what the optional secret protects.

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?

Short and front-loaded: the change conditions come first, then the polling instruction, then limits and storage. Almost every clause earns its place. The 'for the person you work for' framing is the one mildly expendable phrase.

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 no annotations and no output schema, the description must stand alone, and it covers the essentials: what triggers a notification, how to poll, the cap, and what data is stored. Remaining gaps (limit-exceeded behavior, error output, secret semantics) are minor but real for a subscription-mutating tool.

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 all three parameters are already documented, making 3 the baseline. The description adds only marginal meaning — 'Stored: the address and your agent name' clarifies that name is a persisted identity rather than a label, and the 3-site cap contextualizes url. The secret parameter's purpose is left entirely to the schema.

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 behavior on a specific resource: being notified when a site's agent-readiness changes (bot blocked, llms.txt gone, or fixed). That is far more than a restatement of the name, and an agent can infer it is a persistent subscription rather than a one-off check. It does not explicitly name the siblings it differs from (check_site for a one-off probe, unwatch_site to stop), so it stops short of 5.

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 gives real operational guidance: 'call my_watches once a day' routes the agent to the polling sibling and implies how to consume results. It also states a hard cap ('Up to 3 websites'). But it never says when NOT to use it — e.g. use check_site for a single snapshot, or unwatch_site to cancel — so the contrast with alternatives is left to inference.

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