OnChainDiligence Payment Evidence

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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=true, and the description goes well beyond them: it states the tool 'never sends, signs or authorizes payment' and that the receipt's policy is UNKNOWN (no agent identity, wallet ownership, provider identity or service-delivery claim). That last disclosure is indispensable for correctly interpreting the returned evidence and is not available from any structured field.

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?

Four tight sentences, front-loaded with the usage trigger, then the non-authorization guarantee, the scope limitation and the retry rule. No sentence is filler; minor jargon ('OCD receipt') is the only friction.

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 only two fully documented parameters, no output schema and annotations covering the safety profile, the description supplies everything else an agent needs: timing, non-authorization, the limits of what the receipt proves, and retry semantics. Nothing material 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 description coverage is 100%, so the baseline is 3. The description adds the useful qualifier that the network and transaction reference must be the 'exact' observed values, reinforcing what the schema already documents (EVM hash / Solana signature, no credentials).

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: independently observe a completed payment's network/transaction reference and 'create or return a signed OCD receipt.' The pre-condition ('after a supported payment has occurred') sharply separates it from get_receipt, inspect_payment and verify_receipt, but none of those siblings is named explicitly, so an agent must infer the routing.

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?

It tells the agent exactly when to call it ('after a supported payment has occurred') and how to recover ('Pending requests must be retried with the same reference, not another payment'). It does not name an alternative tool or state a when-not condition, so sibling selection is left implicit.

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 readOnly/openWorld=false, but the description adds substantive behavior: the return is the unchanged signed envelope or a bounded not-found reason, private and unknown IDs are deliberately indistinguishable, retrieval performs no proof verification, and receipt content is untrusted data rather than instructions. These are security-relevant traits annotations cannot express.

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?

Front-loaded with the usage condition, and every subsequent clause carries real information (access scope, return shape, verification boundary, trust boundary). It is dense and slightly run-on, but there is no filler sentence to cut.

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 return-value semantics itself (signed envelope or bounded not-found reason) and covers access limits, ID-privacy behavior, and the trust boundary on returned content. Nothing an agent needs to call or interpret this tool 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% and the schema already says 'exact public OCD-RCP receipt ID; never a private credential', so some of the description's wording overlaps structured data. It still adds meaning by stressing the ID must be exact and by explaining that unknown and private IDs are indistinguishable at retrieval time, which is not in the schema.

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 (retrieve a receipt by exact public ID) and immediately bounds the scope: cannot search or list, no payment/publication/private-operation access. It also names the sibling that handles proof checking, so an agent can distinguish it from verify_receipt without opening either 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?

Gives an explicit triggering condition ('when the user has an exact public OCD-RCP receipt ID') plus a concrete example intent ('what a payment receipt contains'). It also states the exclusion (no search/list) and routes emulation to the alternative ('use verify_receipt for that').

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?

Goes well beyond the readOnlyHint/openWorldHint/destructiveHint annotations: it discloses the three possible verdicts, that it performs no external lookups, no storage, no receipt, and critically that ALLOW means policy comparison only and is not a compliance/sanctions certification. This is exactly the kind of semantic caveat an agent needs to avoid over-trusting the result.

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?

Front-loads the usage trigger, then packs verdicts and scope exclusions into two dense but purposeful sentences. No filler, though the final sentence mixing amount-format and URL-credential rules is slightly compressed.

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 correctly supplies the return values (ALLOW/REQUIRE_APPROVAL/BLOCK) and the safety semantics around them, which is the essential missing piece. Remaining gap is the unexplained acknowledge_unconstrained policy flag given the deep nested schema.

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% and the nested objects contain many fields (action.kind/asset/amount/sender/network/resource/recipient, plus policy fields), so the description must carry the load. It usefully specifies decimal amounts vs atomic units, public addresses, and that resource URLs are never fetched and must not carry credentials — but leaves policy fields such as acknowledge_unconstrained and expected_payer unaddressed.

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?

Names a specific verb and resource ('check a proposed payment against explicit rules before sending it') and states the exact decision outputs (ALLOW, REQUIRE_APPROVAL, BLOCK). Explicitly carves out what it is NOT (no send/sign/authorize, no sanctions screening, no compliance certification), which cleanly separates it from the receipt-oriented siblings.

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?

Opens with a direct when-to-use trigger ('Use this when the user wants to check a proposed payment...before sending it') and gives concrete example conditions (amount, recipient, asset, network vs policy/limit). Negative scope ('does not send, sign or authorize') further constrains when this is the right tool.

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?

Adds substantial context beyond the readOnly/non-destructive annotations: it returns one of three status codes, needs no credentials or payment authorization, envelopes are not published or echoed, and it discloses the trust model (fetches OCD's public key registry, trusts this server) plus the limits of VALID. The only wobble is that this 'online check that fetches a registry' sits in mild tension with openWorldHint=false, though the fetch is to the service's own registry.

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?

Front-loads the trigger condition and the return values, then layers the caveats about what VALID does and does not mean. It is long but nearly every clause carries decision-relevant information; a couple of sentences could be tightened.

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 explaining returns and does so fully (VALID/INVALID/UNVERIFIABLE with the precise meaning of VALID and its non-guarantees), plus the no-credentials envelope privacy rule. 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 50% (receipt_id is undocumented in the schema), and the description compensates by framing the two inputs as mutually alternative ('one public receipt_id OR an envelope'), stressing the receipt_id must be public, and defining what it is safe to put in an envelope (no credentials, no payment authorizations). It adds real meaning over the schema.

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 (verify) and resource (an OCD receipt proof), and immediately clarifies the question it answers: whether a receipt is authentic or its evidence signature checks out. This is clearly distinguishable from siblings like get_receipt or inspect_payment, which retrieve rather than validate.

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?

Gives a clear trigger condition ('Use this when the user wants to know whether an OCD receipt proof is valid') and names an alternative approach (offline verification is stronger). It does not explicitly contrast with the sibling retrieval tools, so it stops short of full when/when-not routing.

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