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

Annotations are empty, so the description must disclose behavior, but it only restates the purpose. It does not reveal whether the operation is read-only, whether it requires network access, what constitutes a 'material change', or what the output looks like. For a diffing tool, one might expect context about case sensitivity, text normalization, or whether the change detection is semantic vs. lexical. None of that is present.

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 a single, well-structured sentence that front-loads the core action ('Compare two versions') and then enumerates the relevant economic terms. There is no fluff or repetition; every word contributes to understanding the tool's purpose and scope.

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 simple two-parameter tool, the description is reasonably complete in conveying intent. However, it does not address edge cases (e.g., empty input, identical strings) or output semantics. Since there is no output schema, one might expect the description to explain the return value, but it doesn't. Given the tool's simplicity, the lack of return-value documentation is a minor gap, but the absence of input format details (plain text, markdown, etc.) prevents a higher score.

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 explain the parameters. The phrase 'two versions of commercial text' gives an agent a rough idea that 'beforeText' and 'afterText' hold the original and new versions, but it doesn't specify constraints like text encoding, length limits, or required language. The schema already names the parameters clearly, so the description adds minimal value beyond the parameter names.

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 uses a specific verb ('compare') and resource ('two versions of commercial text'), and enumerates a concrete list of economic terms it detects changes in (pricing, fees, payout, commission, eligibility, renewal, restrictions, SLA). This leaves no ambiguity about the tool's function and it clearly distinguishes itself from siblings through the use of 'diff' in the name and the explicit scope of 'commercial text'.

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 gives no guidance on when to use this tool instead of a sibling. It does not state prerequisites, expected input format, or any conditions that would make this tool preferable. There is no mention of alternatives or exclusion criteria (e.g., 'if you need to search, use different_tool'), so an agent receives no help in routing.

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