cursor_diff

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

With no annotations provided, the description must carry the behavioral burden. It conveys that this is an inspection/read operation with optional raw patch inclusion and paging, but it does not disclose whether the job must be finished, error behavior for invalid job IDs, authentication requirements, or output size limits beyond the patch parameter.

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 compact sentences, front-loaded with the core purpose and followed by the key paging behavior. Every sentence earns its place.

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 four-parameter inspection tool without an output schema, the description is mostly complete: it names the main return components (changed files, diffstat, optional raw patch) and explains paging. It leaves minor gaps around job state requirements and error behavior, but nothing critical for correct invocation.

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 50%, with limit and includePatch documented in the schema. The description adds meaning for offset/limit as paging controls for large patches, but it does not explain the offset semantics or clarify that jobId refers to an execute job beyond the phrase 'execute job changed'.

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 clear verb and resource: inspect what an execute job changed, including changed file list, diffstat, and raw patch. It does not explicitly differentiate from siblings like cursor_status or cursor_run, but the 'execute job changed' scope is specific enough for an agent to identify the tool.

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 implies usage after an execute job and explicitly says to use offset/limit when paging through a large patch. However, it does not state when to use this tool versus cursor_status or cursor_run, nor does it mention prerequisites such as the job needing to be complete.

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