crosscheck

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

With no annotations at all, the description carries the full disclosure burden, and it does so thoroughly. It states the three return values, reveals that counts, required JSON fields, and sums are checked in code, notes that payment_tx is verified on chain, and fully explains the unusual x402 payment flow including the PaymentRequired error and retry mechanism. Cost is also disclosed. This is exemplary transparency.

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 longer than average, but every sentence earns its place—core function, return behavior, cost, and the non-obvious payment protocol are all necessary. The structure is front-loaded with the tool's main purpose, followed by return semantics and then payment details, which is a logical and efficient ordering.

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?

This is a paid, externally-dependent tool with no output schema and no annotations, so the description must cover invocation, cost, and return values—and it does all of these. It even explains the client-side payment retry protocol and how to use the fallback npm client, leaving little room for guesswork. The term 'verify_externally' is not expanded, but it is reasonably self-explanatory given the context.

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 meaningful value beyond the schema: it clarifies that payment_tx is verified on chain and that checks in code cover counts, required JSON fields, and sums, which gives task and deliverable real semantic weight. This justifies a point above baseline.

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 precise verb-resource pair: 'Checks work another agent handed back against the task it was given.' It clearly explains the purpose and the pre-payment/escrow context, and the unique return values (accept, reject, verify_externally) help separate it from vague siblings like 'check' and 'result'. However, it never explicitly names a sibling or contrasts itself, so it stops just short of full 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 clear trigger conditions: 'before you pay, release escrow, or pass it on.' It also explains how to invoke payment, either through an x402-aware MCP client or the npm client, which is important operational guidance. But it does not discuss when to prefer alternative sibling tools or what would make this tool inappropriate, so it lacks explicit when-not guidance.

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 burden and does so richly: it discloses pricing ($0.02, +$0.01 per fetched page), the x402 payment mechanics including the first-call PaymentRequired/retry flow, that a dead cited link fails the draft, that arithmetic is recomputed in code, and that open_review is not routed yet. This is unusually complete behavioral disclosure.

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 purpose then modes, and most sentences earn their place. The payment paragraph is dense and slightly overpacked for a tool description, but it is information the caller needs and is not repeated elsewhere.

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?

There is no output schema and no annotations, so the description must cover both return shape and safety/payment context — it does ('Returns pass or specific issues with fixes') along with pricing, auth via x402 or the npm client, and the free-tier identity path. Nothing essential to calling 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%, so the baseline is 3, but the description adds real meaning: it explains what 'request' triggers (scope/period/question checks) and what 'sources'/'source_urls' enable (grounding plus crosscheck fetching up to 3 pages itself, with per-page cost). It adds operational semantics beyond the schema's field descriptions.

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 ('Independent review of a draft') with examples of the artifact types it accepts, and immediately describes output shape ('pass or specific issues with fixes'). An agent can distinguish this review tool from siblings like verify_receipt or skillcheck without opening any 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?

Clearly frames the when: 'before its human sees it', and then conditions each mode of use ('With request ... it also checks ...'; 'with sources ... each claim is checked'). It stops short of explicitly naming alternative siblings to route to, so it's strong context but not full when-not guidance.

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 burden of behavioral disclosure. It does add useful traits: the operation is free, it returns status/verdict/signed receipt, and it relates to an earlier asynchronous paid call. However, it does not disclose whether retrieval is one-time or repeatable, whether authentication is required, or any rate limits. Adequate but with notable gaps.

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, tightly packed sentence. 'Free.' is front-loaded and immediately communicates a key trait. Every remaining phrase adds meaning: what is returned, the context, and the required inputs. No filler or redundancy.

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 simple two-parameter read tool with no output schema and no nested objects, the description covers the essential points: what the tool returns, when to use it, and what inputs are needed. It does not explain error cases or polling behavior, but those are not critical for this straightforward retrieval operation.

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 both parameters already have descriptions saying they come from the paid call. The description's phrase 'using the job_id and result_token it returned' adds little beyond the schema. Baseline 3 is appropriate because the schema already documents the parameters sufficiently.

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 the resource and action: retrieving the status, verdict, and signed receipt of an earlier paid call using job_id and result_token. It goes beyond the title 'Get a result' by specifying the content of the result. It does not explicitly differentiate from sibling tools like check or skillcheck_lookup, so it stops short of a 5.

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 states the triggering context: an earlier paid call was still running and returned job_id and result_token. This implies the tool is the follow-up retrieval step for asynchronous calls. It does not explicitly name alternatives or exclusions, but the usage context is clear enough for an agent to select it appropriately.

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 so excellently. It discloses that the tool reads and never runs, that it never claims safety, and it thoroughly explains the payment mechanism, including the x402 error flow and retry behavior. This is far beyond typical transparency and leaves no ambiguity about side effects or costs.

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 dense but every sentence earns its place: purpose, safety, pricing, payment flow, and client instructions. It front-loads the core purpose and safety, then details the payment mechanism without fluff. The structure is logical and efficient, making it easy for an agent to parse quickly.

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 (payment, error handling, client requirements), the description covers nearly all necessary context: what it does, how to pay, what happens on first call, and how to retry. It does not explicitly describe the return value format, but it states 'Never says safe,' implying a judgment output. Since there is no output schema, a bit more detail on the return could improve completeness, but overall it is quite thorough.

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 schema already documents all three parameters (files, ref, fresh) with descriptions. The tool description does not add extra meaning about these parameters beyond what the schema provides, such as format or constraints. It mentions 'read, never run' but that is not parameter-specific. Thus, a baseline 3 is appropriate.

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 states the tool performs a security review of a skill or MCP server's files, with the key qualifier 'read, never run.' This is a specific verb-resource pair that distinguishes it from typical execution tools. However, it does not explicitly name sibling tools like accept, check, result, or skillcheck_lookup to differentiate them, so it falls short of a perfect 5.

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 context: 'before you install or connect it' and explains when it is free vs. paid based on prior scans. It also details how to use it with an x402-aware client or the npm fallback. It does not explicitly mention alternatives or when not to use this tool, but the context is strong enough for an agent to decide.

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. It discloses that the operation is free and that it returns the 'latest' skillcheck for an 'exact' bundle, but it does not mention error handling (e.g., invalid hash, no matching bundle), response format, or any side effects. It omits critical behavioral context an agent would need for robust invocation.

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, information-dense sentence. It front-loads the cost ('Free') and then states the core purpose and the exact input requirement. Every word contributes value; there is no redundancy or fluff.

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 tool with a single parameter and no output schema, the description adequately explains the input and the general behavior, but it does not specify what the tool returns (e.g., the skillcheck object, a status, or an error message). It also lacks guidance on edge cases like nonexistent bundles. Given the lack of an output schema, the description should have clarified the return value to be fully complete.

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 a pattern for the parameter, but the description adds substantial meaning: it explains that bundle_sha256 is the SHA-256 of the canonical JSON of files sorted by path, each as {path, sha256}. This is a detailed semantic definition that goes far beyond the schema, giving the agent precise instructions on how to construct the input.

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 ('look up'), a resource ('latest skillcheck'), and a precise identifier ('bundle_sha256') with a detailed definition of that hash. It clearly distinguishes this tool as an exact-match lookup by hash, setting it apart from broader sibling tools like 'skillcheck' without needing explicit naming.

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?

There is no guidance on when to use this tool versus alternatives. It does not mention scenarios like 'when you have the exact bundle hash' or 'for fuzzy lookups use another tool'. The description is purely functional and offers no selection criteria or exclusions.

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 the behavioral burden, and it does disclose meaningful traits: the operation is 'Free' (cost transparency) and it validates issuer, signature, outcome, and coverage. However, it never states that the operation is read-only/non-mutating or what the verification response looks like, and there is no output schema to fill that gap.

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?

Purpose and the 'before trusting' trigger are front-loaded, and the second sentence efficiently bundles all parameter guidance. The cost aside 'Free.' is terse and useful, though the long second sentence lists many parameters in a dense run-on.

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 9-parameter, zero-required, no-annotations, no-output-schema tool, the description covers the core action, the trust rationale, and per-type input guidance. The noticeable gap is the absence of any statement about the return/verification result shape, which the missing output schema leaves undocumented.

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% and the schema already labels each parameter with its receipt-type context (e.g., 'accept: the task the receipt should cover'), so the description's mapping of draft/request/sources/task/deliverable/files to receipt types largely restates structured data. It confirms the receipt_hash-or-receipt alternative but adds little 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 description states a specific verb (verify) and resource (crosscheck receipt) and enumerates exactly what is validated: issuer, signature validity, outcome, and text coverage. This clearly distinguishes it from siblings like check, accept, and skillcheck, which appear to produce the receipts this tool verifies.

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 gives a clear trigger condition ('Before trusting work that arrives with a crosscheck receipt') and even maps which inputs apply to which receipt type (check/accept/skillcheck). It does not explicitly name alternative tools or state when NOT to use this one, keeping it 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.