editor_patch_apply

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

Annotations declare readOnlyHint=false, asserting the tool mutates its environment, while the description explicitly says writes are disabled and only an error code is returned, i.e. the tool is effectively read-only. This directly contradicts the structured annotation, so it scores 1 despite the useful disclosure of the disabled state.

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?

A single, front-loaded sentence with no filler. It is efficient, though the colon construction compresses the error code and rationale into one clause that could be marginally clearer.

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 stubbed tool that only returns an unsupported-capability signal, communicating that fact is the main requirement, and no output schema or parameter docs are needed to act on it. The missing piece is any guidance on what the agent should do instead of applying the patch.

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?

All five required parameters (buffer_id, offset, expected_hex, replacement_hex, preview_token) have 0% schema description coverage, and the description supplies no meaning for any of them. The only oblique hint is that they relate to an unsaved-buffer write, which is far short of compensating for the gap.

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 concrete action (report CAPABILITY_UNSUPPORTED) and the specific resource it concerns (atomic unsaved-buffer writes), so an agent understands this call is a no-op error report rather than a patch application. It does not, however, name or exclude siblings like editor_patch_preview or binary_patch_apply, so differentiation is left implicit.

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 the tool is unusable ('disabled this release') but never states when to reach for it versus editor_patch_preview/binary_patch_apply, nor what the agent should do instead. There is no explicit when-to-use, when-not-to-use, or alternative routing.

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