preview_memory_patch

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

The description says 'without writing', but the annotation declares destructiveHint=true, which is a direct contradiction. Additionally, it doesn't disclose what happens on a mismatch (e.g., whether it returns an error) or what the preview output contains.

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 a single, efficient sentence that front-loads the core purpose. There is no wasted wording, and the key constraint 'at most 64 bytes' is included.

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?

The tool has 4 required parameters, no output schema, and low parameter documentation. The description does not explain how to obtain an edit session, what the preview returns, or how the tool fits into the broader workflow. It is insufficient for safe or 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?

The schema description coverage is only 25% (only 'address' is described), and the description adds little meaning. It mentions 'expected bytes' but doesn't explicitly link to expectedHex, and it doesn't explain editSessionId or replacementHex. With such low coverage, the description should compensate but doesn't.

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 compares expected bytes and previews a patch without writing, using specific verbs ('compare', 'preview') and a resource ('patch'). The phrase 'without writing' implicitly distinguishes it from apply_memory_patch, though it doesn't explicitly name that alternative.

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?

There is no guidance on when to use this tool versus siblings, no mention of prerequisites such as an active edit session, and no explanation of how it relates to apply_memory_patch or undo_last_patch. The description only states what it does, not when to use it.

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