USDC & RPC Reference (free)

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real context beyond that: the payment rail (USDC on Base) and a preview of the catalog's contents, telling the agent what it will get back before calling.

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?

A single front-loaded sentence with the resource named first and the enumeration placed after it. No filler and nothing to trim.

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 no-parameter, read-only catalog tool with no output schema, the description supplies everything needed: what is listed, the currency/network, and the identity of each item. An agent can call it correctly with no further information.

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?

Zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No misleading parameter claims are made.

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+resource ('Lists the pay-per-call x402 HTTP endpoints on this site') and enumerates the exact entries returned (Safe Read, x402 Preflight, Seller Field Guide). Siblings (rpc_getlogs_limits, usdc_token_info) are unrelated, so no differentiation is needed.

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 parenthetical notes each entry's purpose (e.g. 'check an x402 endpoint before paying'), which implies when an agent would care, but there is no explicit 'call this when…' guidance or statement of prerequisites. Usage is inferable rather than stated.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The word 'Measured' hints the values are observed rather than guaranteed, which is useful context, but the description never says whether this is a static snapshot or a live probe, or how fresh the measurements are.

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?

Two sentences, no filler, with the data-domain summary front-loaded and the parameter note second. The opening is a verbless noun phrase, which is slightly less scannable than a verb-first statement, but nothing is wasted.

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, the description carries the burden of describing return shape; it partially does so by enumerating the four measured dimensions, which is genuinely helpful. It still omits the response structure, how many endpoints are covered, and whether results are cached — gaps an agent would notice on first call.

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% and the schema already documents 'Chain id or slug, e.g. 1 or ethereum', so the description repeats rather than extends it. The one added nuance is that the parameter filters rather than selects — implying an unfiltered call returns all chains — but that inference is left implicit.

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 names a specific resource — measured eth_getLogs limits, latency, archive support and error messages — for free public RPC endpoints, which makes the tool's output domain unambiguous. It lacks an explicit verb (is it 'get', 'compare', 'list'?) and does not reference either sibling, though the siblings are far enough away in domain that confusion is unlikely.

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 only guidance is 'Pass chain (id or slug) to filter,' which is a parameter instruction rather than a when-to-use rule. Nothing tells the agent when this beats querying an endpoint directly, whether it covers only free/public providers, or what happens if chain is omitted.

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

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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description is consistent with a safe read. It adds genuinely behavioral detail beyond the annotations — that values are verified onchain and that omitting chain switches to an all-chains listing mode. Return field names are given, though per-field formats and any caching/freshness behavior are not.

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?

Two sentences, no filler. The returned-fields list comes first and the calling convention second, so the highest-value information is front-loaded.

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, the description compensates by enumerating the return fields, so an agent knows what it will get. For a one-optional-parameter read tool with annotations, nothing needed to call it correctly is missing.

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% with a single documented parameter, so the baseline is 3. The description adds the important semantic that the parameter is optional and that omission means 'list all chains', which the schema's description does not state, plus a second concrete example.

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 resource and enumerates exactly what is returned: contract address, decimals, EIP-712 domain (name, version, domainSeparator) and EIP-3009 support, plus the 'verified onchain' qualifier. An agent can tell instantly this is a metadata lookup, not an RPC call or payment tool.

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?

Explicit invocation guidance: accept a chain id (8453) or slug (base), and omit the parameter to list all chains. That covers the main decision the caller faces. No exclusions versus alternatives, though the sibling tools are unrelated so there is little to differentiate.

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