DiffMint by Harlo

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description goes beyond them by disclosing the failure mode ('applied:false if a hunk does not match') and the successful return value (patched text), which is exactly the behavior an agent needs to plan error handling.

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 tight sentence with the core action first, followed by the failure mode and the optional tolerance. No filler, nothing that could be cut.

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?

Good that it states the return shape since there is no output schema, and the hunk-mismatch case is covered. But with 33% schema coverage and no explanation of fuzz behavior or how multi-file patches are rejected, an agent still has gaps before invoking it confidently.

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 33%: only 'patch' is described in the schema. The description mentions 'text' as the target and 'fuzz 0-2', but the fuzz bounds merely restate the schema's minimum/maximum and it never explains what fuzz actually does (tolerated context mismatch), which is the one piece of semantics the schema cannot convey.

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?

Specific verb+resource: 'Apply a single-file unified diff (patch) to text', with the return value named. The 'single-file' qualifier bounds scope usefully. It does not name diff_text or text_similarity, so an agent must infer the contrast from the verb alone.

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 reach for this tool versus diff_text or text_similarity, nor any precondition guidance (e.g., patch must target the supplied text). Only the implicit 'single-file' scope limit hints at usage limits.

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

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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description adds substantial context beyond that. It discloses the algorithm, size limits per mode, the 250-unit 422 cutoff, patch applicability limits, and statelessness/no logging/no URL fetching.

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 dense but front-loaded: purpose and modes come first, followed by output characteristics, determinism, limits, failure behavior, and statefulness. Every sentence adds useful information without repetition.

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 and nine parameters, the description does a strong job covering return formats, limits, errors, and statelessness. The remaining gap is that a few optional parameters and their behavior are left to the schema alone.

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 low at 33%, so the description must carry the burden; it explains mode values and defaults, output formats, and that ignore_whitespace is lines-mode only. However, several optional parameters such as context, label_a, label_b, and ignore_case are not described, leaving some gaps.

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 and resource ('Compare text a with text b') and immediately enumerates modes (lines, words, chars). It also distinguishes the tool from semantic comparison siblings by stating it is a deterministic Myers diff, not an AI or semantic comparison.

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?

It clearly states the default mode, the available modes, and important limits and failure behavior (422 too_different). It also rules out 3-way merge and binary files, but it does not explicitly route the agent between this tool and the sibling apply_patch or text_similarity.

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

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.