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

No annotations are provided, so the description carries the full behavioral burden. It does usefully disclose the return format ('unified diff') and that only the most recent change is returned, but says nothing about behavior when no change has been detected, whether the watch id must exist, or whether the diff is repeatable or consumed on read.

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 sentences, front-loaded with what it returns, followed by the trigger condition. No filler or redundancy.

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?

A simple one-parameter read tool with no output schema, and the description sufficiently covers what comes back (a unified diff of the latest change) and when to call it. Minor omissions: no-change behavior and watch-existence prerequisites.

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% and the single parameter is documented as 'Watch id'. The description's phrase 'for a watch' only loosely ties the id to a watch; it adds no filtering semantics or format detail beyond the schema, so baseline 3 applies.

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?

States a specific verb and resource ('Get the unified diff') scoped to 'the most recent detected change for a watch', which implicitly separates it from the broader watch_history sibling. It does not name that sibling explicitly, so the distinction relies on inference.

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?

Gives a concrete trigger — 'Use after watch_check reports changed=true' — naming the sibling whose output selects this tool, plus a second valid use case ('report what changed since you last looked'). No explicit when-not-to-use guidance (e.g., older changes via watch_history).

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