editor_patch_preview

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds non-obvious behavior beyond that: the result's can_apply flag is false and no mutation token is issued, telling the agent this call cannot be chained into a write. That is genuinely useful state/auth context not present in the structured fields, though return shape and pagination/scope behavior remain unstated.

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 short clause with no filler; the read-only guarantee is front-loaded. It is efficient, though the extreme brevity is under-specification rather than true conciseness, which keeps it from a 5.

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?

With four required, completely undocumented parameters, no output schema, and a write-adjacent preview role, the description is far too thin. It never explains the argument contract (what expected_hex/replacement_hex must contain) nor what the preview returns beyond can_apply. Annotations cover the safety profile, but the operational contract is missing.

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% for all four required parameters (buffer_id, offset, expected_hex, replacement_hex), so the description carries the full burden and provides nothing. It gives no hint about offset semantics, hex encoding expectations, or what buffer_id identifies. An agent cannot construct a valid call from the description plus schema alone.

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 gives a verb pair and an object ("Verify and preview live bytes"), so the agent can infer this is a dry-run check rather than a mutation. However, it never says what is being verified against (the expected_hex parameter) and offers no differentiation from the near-identical sibling binary_patch_preview, or from the paired editor_patch_apply. The purpose is implied rather than stated.

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 clause "can_apply is false and no mutation token is issued" implies a preview-before-apply workflow and signals this call cannot be the one that commits a change. But no alternative is named explicitly (editor_patch_apply, binary_patch_preview), and there is no stated condition for choosing this tool over its siblings. Usage is only implied.

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