Stabledrop escrow payments

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

No annotations are provided, so the description carries the full behavioral burden. The wording 'what has happened' implies a read-only, historical lookup rather than a mutating action, but it does not explicitly state side-effect-freedom, authorization requirements, or possible response behaviors. This is minimally acceptable but not fully transparent.

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 a single concise sentence with no filler. It front-loads the core concept ('what has happened to a settled payment') and ends with the key input source (`status_url` on its receipt). Slight awkwardness in phrasing prevents a 5, but it is appropriately sized and structured.

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 one required parameterhare and an output schema present, the description does not need to explain return values. It adequately names the input source and settled-payment precondition, but it omits contextual details such as whether this is safe to call repeatedly, whether the `status_url` expires, or how this relates operationally to `settle_escrow_payment` and `verify_escrow_receipt`.

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. It adds useful meaning by explaining that `status_url` comes from the payment receiptcars, but it does not provide details about URL format, how to extract it, or what the tool expects beyond the schema's plain string type. The single-parameter design reduces the risk, but the semantics are only partially enriched.

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 clearly identifies a specific action: checking what happened to a settled payment using the `status_url` from its receipt. It distinguishes itself from sibling tools like `settle_escrow_payment` and `verify_escrow_receipt` by focusing on status/history of an already settled payment, though the phrasing 'what has happened' is somewhat indirect.

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 implies the tool is meant for post-settlement inquiries: the payment must be settled and the caller must have the receipt's `status_url`. It does not explicitly name alternatives or state when not to use this tool, so usage context is clear but exclusion/routing guidance is missing.

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?

With no annotations, the description carries the behavioral burden and does disclose the output (a QR containing token, network, destination, and amount) and the critical encoding behavior (URI, not bare address). It does not explicitly state side-effect status or failure behavior, but for a pure encoding/rendering tool this is reasonably transparent.

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 first two sentences are concise and front-loaded, but the two all-caps warnings are verbose and partly explain design rationale rather than operational requirements. The content is useful, but the description could be tightened without losing meaning.

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 one-parameter tool with no output schema and no annotations, the description is largely complete: it names the input source, describes the output, and warns about the key misuse. It could be more explicit about the exact QR/image format returned and error cases, but these are minor gaps.

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?

The single `payment_uri` parameter is given provenance ('from `prepare_escrow_payment`') and semantic content (token, network, destination, amount). Since the input schema only says 'string' and schema description coverage is 0%, this fully compensates for the missing schema documentation.

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: it 'Returns a QR a phone wallet can scan' for a payment request, with a clear purpose. It also distinguishes itself from prepare_escrow_payment by audience ('A person who needs the code asks for it').

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?

Explicitly instructs the caller to pass the `payment_uri` from `prepare_escrow_payment` and explains when the tool is appropriate. It also clarifies that it is intentionally separate from `prepare`, so an agent knows not to expect this output embedded in the machine-readable result.

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?

With no annotations, the description carries the full transparency burden and carries it very well. It reveals the key behaviors: email-to-wallet resolution, same address regardless of funding path, generated external_id and the danger of sending a different one, amount units, expiry_timestamp semantics with no default, description length validation, and the EIP-3009 relay mechanics. An agent gets a realistic model of side effects and failure modes.

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 long but well-structured with bolded options, explicit warnings, and front-loaded purpose. However, the wallet-or-email point is made twice in similar wording, and some explanatory passages are more verbose than strictly necessary. It is justified detail rather than filler, but the duplication keeps it from a perfect conciseness score.

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 complex, high-stakes financial preparation tool, the description is remarkably complete: it covers required parameters, optional parameters, failure semantics, defaults, cross-tool sequencing, and the exact reason the returned external_id must be passed back. The output schema exists, so the description correctly focuses on behavior and preconditions rather than restating return fields.

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 only 25%, but the description compensates thoroughly: it explains amount base units, absolute Unix expiry and the significance of 0, external_id generation and matching behavior, description length and purpose, payer's role in the relay path, and the seller/nominal_buyer email-or-wallet semantics. Every meaningful parameter except the self-evident token_symbol is given practical meaning beyond 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?

The opening line 'Work out where a payment must go, before anybody signs or sends anything' gives a precise verb, resource, and phase of the payment lifecycle. It clearly states the tool returns the escrow address and two funding paths, and explicitly positions it ahead of settle_escrow_payment, distinguishing it from the sibling that actually creates the escrow.

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 gives clear contextual guidance: this is the pre-signing/pre-sending step, and later you 'call settle_escrow_payment with no signature'. It also distinguishes the two internal paths and notes that the relayed path is the only one an agent can complete unattended. It does not explicitly enumerate when to avoid the other sibling tools like check_escrow_payment or verify_escrow_receipt, so it stops short of a perfect alternative-selection guide.

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?

No annotations are provided, so the description carries the disclosure burden. The verb 'Read' signals a non-mutating operation, and the page list clarifies scope, but the description does not mention error behavior, side effects, or return semantics. Since an output schema exists, the lack of return-format detail is acceptable.

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 front-loaded with purpose, then gives a brief rationale, and then a structured list of valid pages. The motivational sentence ('none of it is safe to invent') earns its place by reinforcing when to use the tool, though it is slightly wordy.

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 single-parameter read tool, the description provides the complete set of likely valid page values, the purpose, and the types of questions to answer. It could be slightly more explicit that the listed pages are the only valid values, but the output schema and low complexity mean the description is effectively sufficient.

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?

The input schema provides only a bare `page` string with no description or enum, yet the description compensates fully by enumerating the valid page identifiers (how-it-works, faq, arbitration-policy, terms-of-service, privacy-policy, plugins, home) and explaining what each contains. This is exactly the semantic information an agent needs to select a correct parameter value.

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: 'Read one of the published pages, for answering questions about how any of this works.' It clearly distinguishes this knowledge-base reader from the sibling payment-operation tools (check, prepare, settle, verify) by framing it as the source of authoritative documentation about fees, disputes, and terms.

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 gives strong contextual guidance: 'Use it rather than guessing' and lists the exact topics (fees, dispute resolution, buyer agreements) that should be answered from these pages. It does not explicitly list exclusions or alternative tools, but the context makes the intended use clear enough.

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?

With no annotations provided, the description carries the full burden and does exceptionally well. It discloses that the service checks the address before building escrow, reports if the transfer has not arrived, pays gas in relay mode, holds no key and signs nothing, derives the escrow address from the exact terms, and reports the seller's actual received amount separately from the creator fee. These are real behavioral details beyond the schema.

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 front-loaded with the core purpose and uses bold labels and warning blocks to make long content scannable. However, the sentence about seller and nominal_buyer accepting wallet or email addresses appears twice almost verbatim, which is unnecessary repetition. Otherwise, the length is justified by the two-mode complexity.

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?

Given the tool's complexity, missing annotations, and low schema coverage, the description is remarkably complete. It covers the prerequisite relationship with prepare_escrow_payment, both execution paths, a critical external_id constraint, the impact of altered terms, and receipt/fee semantics. An agent has enough context to call this tool correctly without additional investigation.

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 only 22%, so the description must compensate. It explains the meaning and interaction of the most semantically tricky parameters: seller/nominal_buyer email-to-wallet resolution, authorization/signature relay behavior, external_id provenance, and the relationship between amount, token_amount, and creator_fee. It does not individually define expiry_timestamp, token_symbol, or description, but those are more self-evident or have defaults.

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 first sentence states a specific verb and resource: 'Create the escrow around the money and return a signed receipt.' It also clearly distinguishes itself from the related prepare_escrow_payment by repeatedly referring to 'as prepared' and requiring the external_id returned by that tool, so an agent can tell this is the settlement/execution step rather than preparation or verification.

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 explicitly says 'which one runs is decided by whether you pass a signature,' then gives two clear modes with exact conditions: omit authorization/signature if the transfer was already made, or pass them to have the service relay the payment. It also warns that external_id must be the one returned by prepare_escrow_payment. This gives an agent direct selection criteria.

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?

With no annotations, the description must carry behavioral disclosure, and it does. The warning that the key is fetched from the receipt's own `iss`, not from whoever handed it over, is a critical non-obvious behavior. The note about external receipts also clarifies scope, though it does not explicitly state side effects or error behavior.

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 compact and front-loaded: one purpose sentence, one security warning, one usage sentence. The warning is emphatic but earns its place because it prevents a critical security misuse. There is no filler.

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?

Given a single required string parameter and an output schema, the description covers the purpose, the key security caveat, and the supported input scope. It does not fully compare against sibling tools or document the receipt's wire format, but those are minor given the tool's simple surface.

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?

The schema only provides the parameter name and type, so the description must supply meaning. It does by indicating the receipt carries a signature and an `iss` claim that determines which key validates it. It does not specify the serialization format, but for a single string parameter this is a moderate gap, not a blocking one.

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 action and object: 'Check a receipt's signature against the key its issuer publishes.' This clearly identifies the tool's core function. It does not explicitly name sibling tools, but the usage note about receipts 'from anywhere, including ones this server did not produce' gives some scope differentiation.

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 gives an explicit usage instruction: 'Use this on receipts from anywhere, including ones this server did not produce.' This tells an agent the tool is not limited to receipts the server generated. It does not name alternatives or list when not to use it, so it stops short of full routing guidance.

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