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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds one genuinely useful behavioral trait — the diff output is 'bounded' — plus the default ref orientation, but it never explains what the bound is, whether truncation is signalled, or how a missing file/ref is handled.

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; the verb, resource, scope, and defaults all appear before anything else. Nothing could be removed without losing content.

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 read tool with annotations and no output schema, the description is adequate but thin: it does not explain the bounding limit, whether the diff is guaranteed complete, or the websiteId scope. An agent could call it correctly but would be surprised by truncation behavior.

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 coverage is 75% and the from/to parameters are already documented with their defaults and allowed patterns, so the description largely restates structured data. It does reinforce 'one file name' scope, but adds no format or semantics beyond the schema for name or websiteId.

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 and resource ('Returns a bounded unified diff for one file name between two version refs'), which is clearly distinct from sibling tools like websiteSourceCode_files_read (whole file content) and websiteSourceCode_changes_list (change listing). Scope and default orientation are included in the same sentence.

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 default ('from published to head') implies the common use case of reviewing unpublished changes, but it never says when to prefer this over files_read or changes_list, nor any exclusions or prerequisites. Usage is inferable rather than stated.

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