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

With zero annotations the description carries the whole burden and does so unusually well: it discloses the x402 paid cost ($0.010 USDC/call on eip155:8453), EOA EIP-712-only payment support with ERC-1271/6492 excluded, a 64 KiB MCP body cap, read-only behavior, and two honest caveats that source-export completeness and input authenticity are not established. This is exactly the operational context an agent needs before spending money on a call.

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 core action is front-loaded in the first sentence, followed by output semantics, then operational constraints. Every clause carries distinct information, though the bracketed payment preamble and several compressed caveats make it dense to parse on first read.

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 four-parameter tool with no annotations and no output schema, the description covers the action, the report contents, cost, payment mechanism, size limit, and non-authenticated inputs. The gaps are the undocumented compare_fields parameter and the absence of any indication of the result's shape beyond the three change categories.

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% across four parameters, so the description must compensate and only partly does: 'unique string key fields' explains key_fields and 'keeping missing/null/boolean/number distinct' clarifies comparison semantics. The optional compare_fields parameter (which restricts comparison to named fields) is never mentioned, nor are the 1000-item caps on before/after, leaving the most ambiguous parameter undocumented in both schema and prose.

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 pair — compare two supplied JSON exports using unique string key fields — and enumerates exactly what it reports (additions, removals, changed fields). It never references a sibling tool or explains why one of the many other tools would not do this job, so it is clear in itself but lacks explicit sibling differentiation.

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?

'Two supplied JSON exports' implies the caller must already hold both exports, and 'No database access or writes' boundaries the operating context. However, there is no explicit when-to-use or when-not-to-use statement and no pointer to an alternative for adjacent needs such as duplicate detection, so usage must be inferred.

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