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

Annotations already declare read-only, idempotent, openWorld and non-destructive, but the description adds far more: the at-least-one-of chain/contract/token requirement, the 'protocol needs a chain' failure mode, the truncation behavior for a contract named without a chain, undisclosed testnet exclusion, disagreement handling where both claims are surfaced and neither chosen, and the 'free, no key' constraint.

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 USE WHEN / NOT FOR / RETURNS / READING RULES structure is front-loaded and each block earns its place, especially RETURNS since there is no output schema. It is long, and the READING RULES block restates several fields already listed in the RETURNS shape, so it is slightly over-budget but not padded.

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?

With no output schema and 8 parameters, the description carries the full burden and discharges it: it documents the return envelope, the field-level reading contract (value/as_of/source_url/method/confidence_class, null+reason), staleness semantics, disagreement behavior and the token-list exclusion. An agent has everything needed to call and interpret it.

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 coverage is 100% so the baseline is 3, but the description adds cross-parameter meaning the schema cannot convey: that protocol implicitly requires chain ('add chain' otherwise), that a contract without a chain yields one truncated page, and that two sources disagreeing yields a disagreements block rather than a resolution. That is genuine semantics beyond the per-field docs.

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 USE WHEN clause names a specific verb-and-resource ('the canonical address or id of something on a chain and want it with its source and date') and enumerates concrete examples (Permit2, EntryPoint, USDC/CCTP domain, x402 default asset, chain registry entry). It explicitly separates itself from get_chain_card and scan_recipient, so an agent can disambiguate without opening a schema.

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 NOT FOR sentence names two sibling tools by name with the condition that selects each, and adds a third exclusion ('or a token price'). The USE WHEN clause gives a positive trigger condition. This is explicit when/when-not/alternative guidance.

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