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

With no annotations, the description carries the full burden and delivers: cost ($0.005 USDC/call, x402, eip155:8453), payment constraints (EOA EIP-712 only, ERC-1271/6492 unsupported), body size cap (64 KiB), hard record/field/comparison ceilings, and the caveat that input facts are unauthenticated and the price is experimental. It omits error behaviour, idempotency and what the response looks like, which keeps it below 5.

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 paid/transport marker is front-loaded, then the core comparison semantics, then limits, exclusions and payment constraints — a sensible order. It is densely packed with semicolons and re-states pricing ('Experimental price'), but nearly every clause carries operational information.

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 paid comparison tool with no annotations and no output schema, the description covers inputs, limits, cost and exclusions well, but leaves the agent guessing about the result: are comparisons exact-match after normalisation, is there any tolerance, and how are per-field outcomes returned? Those are core questions for a diff-style tool.

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 compensate, and it partially does: it defines value syntax ('explicit decimal separator, Unicode decimal digits, no grouping'), supported unit conversions (mg/g/kg, ml/l, mm/cm/m), and per-call ceilings (1000 records, 100 fields/record, 5000 fields, 10000 comparisons) that map onto the records array. It never explains the relationship between reference_locale and required_locales, nor what a non-enumerated 'unit' value should be, leaving two of three top-level params under-specified.

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 states a specific verb and resource — compare numeric catalogue fields — plus the alignment keys (exact product, variant, field ID, required locale), which is far more precise than the tool name alone. It implicitly separates itself from currency-type siblings via the explicit 'no currency conversion' exclusion, but never names a sibling tool directly.

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?

Four explicit exclusions ('no prose extraction, semantic translation evaluation, currency conversion or catalogue edits') give real when-not guidance for a domain surrounded by adjacent tools like fx_convert and quote_cost_normalize. It lacks positive when-to-use framing and never names the alternative a user should pick instead, so it stops short of a 5.

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