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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so safety is covered. The description adds genuine value beyond that by disclosing the scoring formula (2 x unchanged chars / total chars), the default granularity, and that change statistics come back alongside the ratio.

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 dense sentence that leads with the core output (the 0-1 ratio) and then adds the formula, granularity, and change stats. Nothing is redundant, though the trailing 'plus change stats' is slightly vague for the space it occupies.

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 read-only 4-parameter tool the description is nearly sufficient, but with no output schema the phrase 'plus change stats' is never unpacked, so the agent cannot describe or reason about the returned payload. The undocumented ignore_case parameter is a smaller residual gap.

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 only 50%: 'a' and 'b' are documented but 'mode' and 'ignore_case' are not. The description compensates for 'mode' by naming the three options and declaring chars as the default; 'ignore_case' is left unstated, though its boolean name is nearly self-documenting.

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 specific verb-form computation (similarity ratio 0-1 between two texts), states the exact formula, and lists the granularity options. It is unmistakably a comparison tool, but it never contrasts itself with the sibling diff_text, so an agent must infer why one would choose similarity over a diff.

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 statement of when to use this versus diff_text or apply_patch. The mention of 'plus change stats' vaguely hints at overlap with diff_text but nothing tells the agent which to pick or under what conditions, so selection is left entirely to inference.

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