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

No annotations are provided, so the description carries the full burden. It does disclose the return shape ('part-level changes plus a unified string'), which is useful since there is no output schema, but it omits any behavioral detail about mode defaults, input size limits, or how the two return representations relate.

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, inputs, and return format all appear immediately. Nothing in it is redundant.

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 no annotations, no output schema, and 0% schema coverage on three parameters, the description should do more. It explains the return shape only vaguely and leaves the mode parameter and its default completely unaddressed, so an agent cannot confidently invoke it without opening the schema.

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% and the description only implies the two text inputs via 'two texts'; it never mentions the 'mode' parameter, its 'lines'/'words' enum values, or the 'words' default. The single non-obvious parameter, which materially changes output, is left entirely undocumented.

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 specific verb ('Diff') and resource ('two texts') and names the output shape, which distinguishes it from siblings like json_diff (which diffs JSON, not free text). It stops short of explicitly routing against any sibling, so it is clear but not maximally differentiated.

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 versus json_diff or when to choose 'lines' vs 'words' mode. The agent must infer that this is for plain text and that mode selection is meaningful, with no conditions or exclusions given.

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