404KIN FIELD Transaction Intent

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

Annotations already say readOnly and idempotent, and the description adds substantial behavioral context: static declaration-only analysis, no chain-state verification, no signing/sending, public/synthetic inputs only, and an explicit expiry date. It also states the output's limited meaning ('not a safety verdict or execution permission'), going well beyond the structured hints.

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 every clause earns its place: purpose, scope, exclusions, output caveat, input constraints, and expiry are all packed into a compact two-sentence structure. The most important purpose is front-loaded before the limitations.

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 comparison tool with no siblings and no output schema, the description covers scope, limitations, safety meaning, input constraints, and expiry, which is strong context. The only gap is the absence of any detail about the report's return format or examples of constructing the nested transaction/expectations objects.

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 carry parameter meaning. It connects expectations to concrete outputs ('excessive allowances', 'wrong recipients', 'collection-wide approvals') and maps 'Ethereum declaration only' to chain_id, but it does not explain transaction.to/data/value semantics or most expectations fields, leaving an agent to infer request construction largely from schema 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 opens with a specific verb and resource: 'Compare supported static ERC20/ERC721/ERC1155 fields with INDEPENDENT caller expectations.' It further clarifies scope ('Ethereum declaration only') and concrete outputs ('Flags excessive allowances, wrong recipients and collection-wide approvals'), so an agent knows exactly what this tool does without sibling comparisons.

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 provides clear negative guidance: it does not verify chain state, contract behavior, or ownership, and it does not simulate, sign, or send. It also warns that a matching report is not execution permission. This tells an agent when not to rely on it, though it lacks a positive 'use this when…' statement; with no sibling tools, exclusions substitute for alternatives.

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