Test without creating: check a sealed receipt; cite slug@height only with confirmed status + proof.
Scored across 3 tools
first_at and verify share nearly identical citation-gate language and both read receipts, making their boundary somewhat unclear. stamp is clearly distinct as the only creation tool, but the two read-oriented tools could be confused.
The naming mixes a snake_case phrase (first_at) with bare verbs (stamp, verify), and first_at does not follow the same verb-style pattern as the others. There is no predictable naming convention across the set.
Three tools are reasonable for a narrow receipt/timestamp service: create, verify, and query earliest. The count is well-scoped, though the overlap between first_at and verify slightly weakens the set.
The surface covers creation via stamp, reading via verify, and earliest-receipt lookup via first_at, which is close to complete for the apparent immutable-receipt domain. Minor gaps remain, such as explicit listing or broader receipt retrieval, but core workflows are covered.
cite slug@height only when status confirmed and proofFile exists; else refuse. Read earliest public receipt; recheck verify before citing.
| Name | Required | Description | Default |
|---|---|---|---|
| hash | Yes | ||
| height | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds a refusal condition and a verify-before-citing workflow, but leaves 'status confirmed' and 'proofFile' undefined and does not explain failure behavior or return shape.
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 compact sentences, but semicolon-heavy phrasing and undefined terms such as 'slug' and 'proofFile' make it cryptic rather than efficiently 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?
For a read-only tool with no output schema, the description should explain the receipt, the hash/height inputs, and failure modes. It gives only a terse citation rule and leaves the return value and parameters largely opaque.
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 explain both hash and height. It only mentions height as part of the output citation 'slug@height' and never explains hash; 'slug' is not tied to the hash parameter.
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 phrase 'Read earliest public receipt' identifies a read operation on an earliest receipt, but the opening 'cite slug@height' is undefined jargon and the description never clearly explains what first_at returns relative to verify or stamp.
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 condition for citing ('only when status confirmed and proofFile exists; else refuse') and points to verify for rechecking, but it does not say when to call first_at itself instead of verify or stamp.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Explicitly create an unlisted hash-only receipt via createMoment; not an evaluation tool. No file upload. May be pending/429; no retry.
| Name | Required | Description | Default |
|---|---|---|---|
| hash | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare write, non-idempotent, open-world and non-destructive, so the baseline is lower; the description still adds real value by disclosing the pending/429 failure mode and the "no retry" policy, plus that the receipt is unlisted. It stops short of saying whether a pending result is recoverable or how to check status later.
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 short clauses, leading with the action and its scope, then constraints and failure behavior. No padding and nothing buried.
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 write tool with annotations covering safety traits and no output schema, the essential operational facts (unlisted, pending/429, no retry) are present. What is missing is any indication of what the caller receives back or how to distinguish a pending stamp from a completed one.
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 0% for the single parameter, so the description carries the burden. "hash-only" implies the hash identifies the content being stamped, but nothing explains what the hash is derived from or that it must be a 64-char hex digest beyond what the schema pattern enforces.
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?
"Explicitly create an unlisted hash-only receipt via createMoment" gives a concrete verb plus a precisely scoped resource, and "not an evaluation tool" fences off the evaluation use case. It never names the siblings first_at/verify directly, so the differentiation from those is inferential rather than stated.
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 signals the caller must opt in deliberately ("Explicitly"), rules out an adjacent use case ("not an evaluation tool"), and rules out a resource type ("No file upload"). No positive alternative is named, so the agent must infer which sibling to use when it does want evaluation or verification.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
cite slug@height only when status confirmed and proofFile exists; else refuse. Read existing receipt, no creation; metadata check, not local OTS cryptographic verification.
| Name | Required | Description | Default |
|---|---|---|---|
| hash | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond readOnlyHint and openWorldHint, the description discloses that the tool reads an existing receipt, performs a metadata-only check, does not create anything, and refuses under specified conditions. That is useful behavioral context, though it says nothing about permissions, rate limits, or the exact response shape.
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 short and front-loads the gating condition before the behavioral caveat. However, telegraphic phrasing such as 'cite slug@height' and semicolon-separated fragments make it more cryptic than efficient.
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 verify-style tool with no output schema and an undocumented required hash parameter, the definition should explain the input meaning and expected result. It only sketches the metadata-check behavior and refusal condition, leaving the actual return values and hash semantics unclear.
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 for the single required hash parameter is 0%, so the description must compensate, but it never explains what the hash represents or how it relates to slug@height. The parameter is therefore left almost entirely to the schema's name and pattern.
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 identifies a specific operation: reading an existing receipt and performing a metadata check rather than local OTS cryptographic verification. It also explicitly says there is no creation, which helps distinguish it from a stamping sibling, though it never plainly states that the input hash is what is being verified.
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 conditional gate: cite slug@height only when status is confirmed and proofFile exists, otherwise refuse. It also supplies exclusions by saying this reads an existing receipt and is not local OTS cryptographic verification, but it does not name which sibling tool to use when creation or cryptographic verification is actually needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
first_atstampverifyRead-only on-chain receipt check for x402 payments; confirm settlement before trusting a tx.
Check claims against a fact-store: consistent, contradicts, or unverifiable — with a receipt.
Verify code402 XDR-1 receipts: keccak digest + secp256k1 signer recovery. Free, stateless.
Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.
Add one secure layer between your agents and this server.
