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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds real behavioral context: the comparison is granular to the bar and tolerates mismatched formats. It says nothing about limits on very large pieces or how differences are summarized, which would have been valuable beyond the annotations.

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 sentence with no filler, front-loaded on the action and finished with the qualifier that matters most. It is efficient, though it leaves the agent with very little to work with given the operation's nuance.

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?

An output schema exists, so the return shape need not be explained, and annotations carry the safety profile. What is present covers inputs, granularity, and cross-format tolerance. Minor gaps remain around size limits and what 'piece' covers, which keeps it below a 5.

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 100%, with both 'a' and 'b' documented as links to versions, so the baseline is 3. The description contributes modestly by implying the two inputs are versions of the same piece and may be in different formats, which clarifies that mismatched formats are acceptable.

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: 'Show what changed between two versions of a piece', with the added scope of 'bar by bar, even across formats'. This clearly distinguishes a diff operation from siblings like convert, render, or transpose. It stops short of naming a sibling it could be confused with, which keeps it from a 5.

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?

Usage is only implied: an agent infers it should call this when it needs a difference between two versions. The phrase 'even across formats' implicitly tells the agent it does not need to call convert first, which is a useful hint. There is no explicit when-not guidance or named alternative.

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