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

Annotations already establish read-only, idempotent, closed-world, non-destructive semantics. The description adds useful behavior beyond that: the return payload ('counts plus a unified diff') and the whitespace/case normalization options, which matter for interpreting results.

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?

Three tight sentences with the core action front-loaded and the guidance rationale second; no filler. Slightly dense in the first sentence but every clause adds information.

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 output schema, the description correctly discloses the return shape (counts plus unified diff). It is nearly complete for a 5-param tool, with the only gap being the roles of 'original' vs 'changed' and the stated default for mode.

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%, so the description must carry the burden. It covers mode (line/word/char) and the ignore_whitespace/ignore_case options, but never explains the 'original' and 'changed' inputs or the default mode='line', leaving two parameters 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?

States a specific verb and resource ('find every difference between two texts') and enumerates the comparison granularities (line, word, char). It is unmistakably distinct from siblings like count_text, check_json, and generate_qr.

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?

'Use this instead of comparing long texts yourself — small changes are easy to miss' gives a clear reason to prefer the tool over manual comparison. It does not name when-not-to-use conditions or alternatives, but the sibling tools are unrelated so there is little routing ambiguity.

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