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

The annotations already declare readOnlyHint and idempotentHint, so the description adds valuable behavioral details beyond them: the exact prefix notation for diff lines and the line cap. This gives the agent a better sense of the output format and limits without needing to invoke the tool.

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 three concise sentences, front-loaded with the primary action and output format. Every sentence earns its place: what it does, the marking style and count, the use case, and the line cap. There is no wasted wording.

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 description covers the core purpose, the exact output format, a practical usage motivation, and a critical limit. With an output schema present to detail the return structure and complete schema descriptions for both parameters, the description is comprehensive for this moderate-complexity tool.

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?

Both parameters ('a' and 'b') have descriptions in the schema ('original (before)' and 'updated (after)'), achieving 100% schema coverage. The description's mention of 'two texts' adds no new semantic detail beyond what the schema already provides, so the baseline of 3 is appropriate.

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's function with a specific verb ('Compute') and resource ('line-by-line diff between two texts'), and details the output format (marking removed/added/unchanged lines plus a change count). It stands out distinctly from unrelated siblings such as base64, color, or count.

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 description provides a clear usage context ('Use to see exactly what changed instead of comparing by eye') and mentions a constraint (capped at 1000 lines per side). However, it does not explicitly name alternative tools or provide when-not-to-use conditions beyond the cap, so it falls short of the highest bar.

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