binary_patch_apply

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false; the description usefully confirms the non-destructive behavior by stating the original is preserved and output is written elsewhere. It does not explain what happens on an expected_hex mismatch, whether the preview token expires, or anything about atomicity/partial writes.

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 tight sentence with the outcome up front and no filler. It is arguably too terse given six undocumented parameters, but nothing in the sentence is wasted.

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 six-parameter mutation tool with no output schema and zero schema documentation, the description leaves the caller without format for hex values, offset interpretation, and token/expected-value failure semantics. It should do considerably more.

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 0% across six required parameters, so the description carries the full burden and mostly fails: path, offset, expected_hex, replacement_hex and preview_token are never explained. Only output_path is obliquely covered by 'new output file'.

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 (apply) and resource (a previewed disk replacement) and adds the key outcome detail that output goes to a new file while the original is preserved. It does not name the preview sibling it depends on, but 'previewed' plus 'disk replacement' distinguishes it reasonably from editor_patch_apply.

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 word 'previewed' implies a prerequisite call to binary_patch_preview, which is useful, but the usage condition is only implied. There is no explicit when-to-use/when-not guidance or named alternative.

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