watch_diff

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

The description adds useful context: it's read-only (returning a patch, no mutation implied), and it's scoped to the 'most recent' change, which is a meaningful behavioral constraint. However, it doesn't disclose things like whether the patch is partial/full, whether there's a limit on patch size, or whether all diff formats are git-specific. Since there are no annotations, the description carries the transparency burden but delivers moderate detail.

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 two sentences with zero wasted words. It front-loads the core function (git patch of most recent change) and then gives a sequencing tip. Every clause adds value.

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?

Given it has an output schema, return values don't need explanation. The description covers purpose, timing (after watch_scan), and content (patch format). For a single-parameter tool with output schema, this is near-complete. Minor gaps: doesn't explain the 'name' parameter explicitly, but the low parameter count and coherent description compensate.

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?

With only one parameter (name) and 0% schema description coverage, the schema provides no semantics. The description implies the tool operates on a named watch but doesn't explicitly state that 'name' refers to the watch name/identifier. The context of 'a watch' plus the single 'name' parameter makes this reasonably inferable, but explicit confirmation would strengthen the parameter documentation.

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 returns 'a watch's most recent change as a git patch' with line annotations. It uses specific verbs and resource ('watch' + diff/patch), and the reference to 'what moved' clarifies the diff nature. It distinguishes from siblings like watch_scan and watch_list by specifying it shows the patch content rather than status.

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 explicit usage context: 'Use after watch_scan reports changed to see exactly what moved.' This clearly tells the agent when to invoke this tool in sequence. However, it doesn't state when NOT to use it or name explicit alternatives, though the sequencing guidance covers the primary use case well.

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