Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.
Scored across 10 tools
The core pair decode_receipt vs verify_receipt is explicitly separated (decode reads fields but does not check the signature; verify checks the signed envelope), and verify_receipt vs verify_evidence_pack is scoped to single receipt vs pack. The only soft overlap is get_sample_receipt vs get_review_pack, both of which surface demo/sample artifacts, and explain_attestation_format is a documentation tool rather than an action, but none of these create real misselection risk.
Nine of ten tools follow a clean verb_noun pattern (decode_receipt, get_public_key, list_my_receipts, verify_evidence_pack, etc.), with get_* and verify_* used predictably for fetch and validation. The single deviation is workspace_summary, which drops the verb and reads as a noun phrase, a minor inconsistency in an otherwise disciplined set.
Ten tools for a receipt verification and transparency service is well-scoped: verification, key retrieval, listing, summary, samples, and format documentation each occupy a distinct slot. Nothing appears redundant enough to cut, and there is no bloat.
The verification lifecycle is largely covered: read, verify, key fetch, list by outcome/policy/model/date, transparency proof, and aggregate summary all exist. Minor gaps remain — there is no tool to fetch or verify a transparency proof directly (only get_transparency_proof to retrieve it), no way to list available policies or issuer key history, and receipt creation is implicitly handled outside the MCP surface.
Read a receipt field by field, with stated limits. Does not check the signature.
| Name | Required | Description | Default |
|---|---|---|---|
| receipt | Yes | The receipt, as a JSON object or a JSON string. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds one genuinely important behavioral boundary beyond them: it parses but does not perform cryptographic verification, which is exactly the fact an agent needs to avoid treating output as trusted. "With stated limits" is vague padding, but the signature caveat carries real value.
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 short sentences with the core action front-loaded and zero redundancy. The phrase "with stated limits" is the one soft spot, gesturing at a constraint without saying what it is.
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, so the description is the only place a caller could learn what a decoded receipt looks like or what happens on a malformed input. "Field by field" hints at the return shape but never enumerates fields or states error behavior, leaving a real gap for a single-purpose decoding tool.
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?
Only one parameter exists and schema description coverage is 100%, with the schema itself explaining the object-or-JSON-string duality. The description adds nothing further about the input, so the baseline 3 applies.
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?
"Read a receipt field by field" names a specific verb and resource, and "Does not check the signature" implicitly separates it from the sibling verify_receipt. The scope is clear, though the sibling is not named outright.
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 exclusion "Does not check the signature" implies that signature validation belongs to verify_receipt, but the description never names that alternative or states positively when to call this tool versus it. The routing signal is inferable rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The receipt format: fields, outcomes, verification commands, and what a signature does not establish. Use before describing the format.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, indicating safe read-only behavior. The description adds value by detailing the content of the explanation (fields, outcomes, verification commands, signature limitations) and the preparatory usage instruction, which goes beyond what annotations convey.
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 two sentences with no superfluous words. It front-loads the purpose in the first sentence and adds usage guidance in the second. Every part earns its place, achieving maximum conciseness for the information conveyed.
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 simplicity (no parameters, no output schema, read-only), the description fully covers what an agent needs: the tool's purpose, the specific topics it explains, and a usage hint. No additional details are necessary for correct invocation or understanding.
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 tool has zero parameters, so the schema coverage is trivially 100%. The description does not need to elaborate on parameters. It correctly does not introduce contradictory parameter information and the baseline score of 4 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 explicitly states it explains the receipt format, listing specific aspects: fields, outcomes, verification commands, and what a signature does not establish. This clearly distinguishes it from sibling tools like decode_receipt and verify_receipt, which perform actions rather than provide explanatory information.
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 includes the directive 'Use before describing the format,' providing a clear contextual cue for when to invoke this tool. However, it does not explicitly mention when not to use it or name alternative tools for different tasks, though the context is strong enough for an agent to infer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the published Seal signing key.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true. The description adds only the resource name ('Seal signing key') but discloses no additional behavioral traits such as authentication requirements, latency, caching behavior, or what happens if the key is unavailable. For a simple fetch, this is minimal value beyond the annotations.
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 consists of a single, efficient sentence with no filler or redundant information. It is perfectly sized for the task and immediately front-loaded with the core action.
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?
Despite the tool being simple (0 parameters, no output schema), the description omits crucial details about the return value (e.g., format, encoding, whether it's a raw key or a JWK) and does not explain what the 'Seal signing key' is used for. An agent would lack the context needed to interpret the result or decide if this tool is appropriate without prior knowledge.
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?
There are no parameters (schema is empty with 100% coverage), so the description does not need to elaborate on parameters. The baseline of 4 is appropriate since the description does not mislead and the absence of parameters is clear. No extra parameter documentation is required.
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 uses the specific verb 'Fetch' and explicitly names the resource as 'the published Seal signing key,' clearly distinguishing this tool from siblings like decode_receipt, verify_receipt, and get_transparency_proof. The purpose is unambiguous and directly aligns with the tool name.
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 provides no guidance on when to use this tool versus alternatives (e.g., should it be used before verifying receipts? Are there prerequisites?). It neither states typical scenarios nor excludes inappropriate use. There is no mention of siblings or constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The published sample evidence pack: fixed review question, bound receipts, disclosure.
| Name | Required | Description | Default |
|---|---|---|---|
| pack_id | No | Pack id. Only the published "sample" pack is available without an account. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the description carries a lighter burden. The description adds useful behavioral context: it specifies that the result is a 'published sample evidence pack' with 'fixed review question, bound receipts, disclosure,' which clarifies the nature of the returned data. No contradictions with annotations. The description doesn't mention auth requirements beyond the parameter hint, but annotations already cover the read-only nature.
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 that states the tool's purpose and key attributes. It front-loads the core function and avoids fluff. Could be slightly improved for clarity, but overall 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?
Given the tool has a simple signature (1 optional parameter, no output schema), the description covers the essential purpose. However, it lacks information about what the output looks like (is it a file? JSON? format?), and the distinction between 'sample' and other packs is ambiguous. The presence of sibling tools like get_sample_receipt suggests potential overlap, and the description does not fully disambiguate. The lack of output schema increases the burden on the description to describe the return value, which it does not.
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% with one parameter (pack_id) that has a meaningful description. The main description adds context about the pack being 'published sample' and its contents, which enhances understanding of what the pack_id parameter refers to. Since there is only one parameter and schema coverage is complete, the description provides additional semantic value 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 it retrieves a 'published sample evidence pack' with specific attributes (fixed review question, bound receipts, disclosure). However, 'published sample' is ambiguous—does it always return the sample pack or any published pack? The verb 'Get' is clear, but the resource scope could be clearer, especially given the single parameter pack_id and the annotation that only the 'sample' pack is available without an account.
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 this tool is for accessing published evidence packs, but it does not explicitly state when to use it vs. alternatives like get_sample_receipt or verify_evidence_pack. Sibling tools suggest a focus on evidence/receipt operations, but no guidance is given on whether this is for general access or only for the sample pack. The context that only 'sample' is available without an account is embedded in the parameter description, not the main tool description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
A genuine signed receipt from the sample workspace (demo key), for trying verification.
| Name | Required | Description | Default |
|---|---|---|---|
| outcome | No | Pick a sample with this outcome. A BLOCKED receipt was signed without the call reaching the provider. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds that the receipt is from a sample workspace with a demo key, providing context beyond annotations. However, no additional behavioral details (e.g., response structure, rate limits) are disclosed. The description does not contradict annotations (annotation_contradiction=false).
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 one sentence with no wasted words. It conveys the essential purpose and source in a concise manner. Every word earns its place.
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 low complexity (one optional parameter, no output schema, clear annotations), the description is fairly complete. It explains what the tool returns and why. A minor improvement would be specifying the return type (e.g., 'receipt object'), but it is not critical for correct invocation.
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%: the single optional parameter 'outcome' has a description in the schema explaining the enum values. The tool description does not add any extra meaning beyond the schema. Baseline is 3 when schema fully describes parameters.
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 returns a genuine signed receipt from the sample workspace for trying verification. This distinguishes it from sibling tools like list_my_receipts (lists user's receipts) and verify_receipt (verifies receipts). The verb 'get' and resource 'sample receipt' are specific and unambiguous.
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 mentions 'for trying verification', which implies a usage scenario, but does not explicitly state when to use this tool over alternatives or when not to use it. No sibling tool comparisons or exclusions are provided. The usage guidance is adequate but minimal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Inclusion proof plus signed tree head for one of your receipts. Requires your aqta_ key.
| Name | Required | Description | Default |
|---|---|---|---|
| attestation_id | Yes | The attestation_id of one of your receipts. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds genuine value beyond that by disclosing the auth requirement (aqta_ key) and the returned artifacts, but says nothing about proof format, error behavior for unknown/foreign attestation_ids, or rate limits.
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 short sentences, zero filler, with the output content front-loaded and the prerequisite trailing. 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?
No output schema exists, so the description carries the burden of describing return values, which it does at a high level (inclusion proof + signed tree head). Complete enough to call correctly, though it stops short of naming the proof encoding or how to feed the result into verify_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 100% and there is only one parameter, so the schema already documents attestation_id fully. The phrase 'one of your receipts' adds a small ownership constraint, but nothing about format or where the id comes from (e.g., list_my_receipts). Baseline 3 applies.
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 pair (inclusion proof + signed tree head) scoped to 'one of your receipts', which is a concrete, non-tautological purpose beyond the title. It does not explicitly contrast with the nearby verify_receipt or decode_receipt siblings, so an agent must infer the split.
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 the prerequisite 'Requires your aqta_ key' and the implicit scoping to your own receipts. There is no statement of when to use this versus verify_receipt (verification) or decode_receipt (parsing), which are the obvious alternatives in the sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List your workspace receipts filtered by outcome, policy, model, or date range. Requires your aqta_ key as Bearer.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max rows, default 25. | |
| model | No | Only receipts for this model. | |
| since | No | ISO timestamp lower bound. | |
| until | No | ISO timestamp upper bound. | |
| policy | No | Only receipts where this policy ran, e.g. pii_scan. | |
| outcome | No | Only receipts with this outcome. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds the authentication requirement and the filtering capability, which are useful. However, it does not disclose any potential pagination behavior, rate limits, or the structure of the returned data (no output schema exists). The description adds some value but is not rich.
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 two sentences with no wasted words. It front-loads the core action and filtering capability, then adds the authentication requirement. Every sentence serves a purpose.
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 6 parameters and no output schema, the description is adequate but incomplete. It does not describe the return format (e.g., list of receipt objects, metadata), nor does it mention default behavior for limit or pagination. The tool is simple, so a score of 3 reflects that the description leaves some gaps for the agent to infer.
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 mentions generic filtering options but does not provide additional meaning beyond the schema's per-parameter descriptions (e.g., limit defaults to 25, ISO format for timestamps). No extra value is added to the parameters.
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 'List your workspace receipts', specifying the verb and resource. It also lists the filtering dimensions (outcome, policy, model, date range), which distinguishes it from sibling tools like verify_receipt or decode_receipt that serve different purposes.
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 mentions the authentication requirement ('Requires your aqta_ key as Bearer'), which is a usage constraint. However, it does not explicitly state when to use this tool versus alternatives (e.g., when to list vs. verify), relying on the sibling names and general context. Minimal guidance on when-not-to-use is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify a review pack receipt by receipt. Each verdict comes from the signed envelope itself, never from stored state, and results are per-receipt, never an average.
| Name | Required | Description | Default |
|---|---|---|---|
| pack | No | A pack object, or "sample" for the published sample pack. | |
| public_key | No | Key to check every receipt against. Omit it to check each receipt against Seal's published issuer keys. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower, and the description still adds real context: verdicts derive from the signed envelope rather than stored state, which is the core trust property of a verification tool. It also discloses that results are per-receipt and never averaged, which shapes how the agent interprets output.
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 tight sentences with zero filler. The granularity claim is front-loaded and the trust-model detail follows immediately; every clause earns its place.
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, so the description must convey the shape of results, and the 'per-receipt, never an average' statement does exactly that at the right level. The main remaining gap is that it doesn't describe what an individual verdict contains, but for a two-parameter verification tool this is close to 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?
Schema description coverage is 100% and both parameters are fully documented there, including the 'sample' sentinel and the published-issuer-key fallback. The description adds no syntax, format, or constraint detail beyond the schema, so the baseline of 3 applies.
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 a specific resource (a review/evidence pack), and 'receipt by receipt' pins down the granularity of the operation. The name/title imply the distinction from the sibling verify_receipt (single receipt), but the description itself never names that sibling, so differentiation is left to the title.
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?
Usage is implied: this is the tool for verifying an entire pack rather than one receipt. However, the description never states when to prefer it over verify_receipt or get_review_pack, nor does it list prerequisites, so the agent must infer the routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check that a record still says what was signed: the permitted or refused decision, unchanged, under Seal's published issuer keys or a key you supply. Handles both formats: ATTESTATION-v1 (a model-call decision) and ACTION-v1 (an agent tool action). No Aqta service in the check.
| Name | Required | Description | Default |
|---|---|---|---|
| profile | No | Usually omit this. The record's own signed version tag selects the format, and ATTESTATION-v1 is the default. Pass 'ACTION-v1' only to force an agent-action record to be checked as one. | |
| receipt | Yes | The record, as a JSON object or a JSON string. | |
| public_key | No | Base64url Ed25519 key to check against. Omit it to check against Seal's published issuer keys; a record carrying any other key then fails. A key you supply is used as given, and issuer_key in the result says whether it is a Seal issuer key. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description reinforces the latter with 'No Aqta service in the check' – i.e. a purely local verification. It adds real behavioral detail: a record with any non-Seal key fails by default, and issuer_key in the result reports whether the key was a Seal issuer key. This goes beyond the annotations without contradicting them.
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?
Three compact sentences, front-loaded with the core purpose and ending with the useful 'no service call' fact. No filler. The final sentence is a clipped fragment, but it earns its place by ruling out a network dependency.
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 more of the burden for describing the outcome, and it only partially does so (it mentions issuer_key in the result but not what a pass/fail result looks like). Annotations cover the safety profile and the local-execution point is made, so the essential context is present, but an agent cannot fully picture the return value.
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 explains profile, receipt, and public_key (including the default-key fallback behavior), and the description largely restates that ('under Seal's published issuer keys or a key you supply'). Per the rubric, a fully documented schema sets the baseline at 3.
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 concrete verb and resource ('Check that a record still says what was signed') and immediately scopes what is being verified: the permitted/refused decision, unchanged, against issuer keys. It also names the two record formats it handles, which helps distinguish it from format-explainer siblings. It does not, however, explicitly contrast itself with decode_receipt or verify_evidence_pack.
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?
Usage is implied rather than stated: the reader infers 'use this to confirm a receipt is authentic.' The description clarifies an option (supply your own key) but never says when to prefer this tool over decode_receipt or verify_evidence_pack, and offers no exclusions or prerequisites. Adequate but with clear routing gaps.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Outcome, model and policy counts across your recent receipts. Requires your aqta_ key.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many recent receipts to summarise, default 100. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds the behavioral requirement of an 'aqta_ key', which is not in the annotations, increasing transparency. However, it does not discuss rate limits, response format, or error handling.
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, front-loaded with the purpose. No redundant information. Every word earns its place.
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 tool with one parameter, no output schema, and annotations covering safety, the description is quite complete. It specifies the output type (counts of three dimensions), the input scope (recent receipts), and a prerequisite. It could mention the output format or default behavior, but it is adequate for effective use.
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% for the single parameter 'limit' with a description in the schema. The description adds context about what is being summarized (outcome, model, policy counts) but does not provide additional semantics for the 'limit' parameter beyond what the schema already states. Baseline of 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 verb 'summarise' and the resource 'workspace decisions' via 'Outcome, model and policy counts across your recent receipts.' It distinguishes itself from sibling tools like 'list_my_receipts' (lists) and 'decode_receipt' (decodes) by focusing on aggregation counts.
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 mentions a prerequisite ('Requires your aqta_ key') but provides no guidance on when to use this tool versus alternatives like 'list_my_receipts' or 'get_review_pack'. There is no explicit exclusion or usage context beyond the tool's purpose.
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.
decode_receipt1 field changedInput schema / properties / receipt / descriptionAdded value: +"The receipt, as a JSON object or a JSON string."get_transparency_proof1 field changedInput schema / properties / attestation_id / descriptionAdded value: +"The attestation_id of one of your receipts."verify_evidence_pack1 field changedInput schema / properties / public_key / descriptionPrevious value: -"Key to pin every receipt against. Omit to use each envelope's embedded key."New value: +"Key to check every receipt against. Omit it to check each receipt against Seal's published issuer keys."verify_receipt1 field changedInput schema / properties / public_key / descriptionPrevious value: -"Base64url Ed25519 key to trust. Omit to use the key embedded in the record, which proves internal consistency only, never provenance."New value: +"Base64url Ed25519 key to check against. Omit it to check against Seal's published issuer keys; a record carrying any other key then fails. A key you supply is used as given, and issuer_key in the result says whether it is a Seal issuer key."verify_receipt1 field changedInput schema / properties / profile / descriptionPrevious value: -"Which format to verify as: ATTESTATION-v1 or ACTION-v1. Omit and the record's own signed version tag selects it."New value: +"Usually omit this. The record's own signed version tag selects the format, and ATTESTATION-v1 is the default. Pass 'ACTION-v1' only to force an agent-action record to be checked as one."verify_receipt3 fields changedInput schema / properties / profileAdded value: +{
+ "description": "Which format to verify as: ATTESTATION-v1 or ACTION-v1. Omit and the record's own signed version tag selects it.",
+ "type": "string"
+}Input schema / properties / public_key / descriptionPrevious value: -"Base64url Ed25519 key to trust. Omit to use the key embedded in the receipt, which proves internal consistency only, never provenance."New value: +"Base64url Ed25519 key to trust. Omit to use the key embedded in the record, which proves internal consistency only, never provenance."Input schema / properties / receipt / descriptionPrevious value: -"The receipt, as a JSON object or a JSON string."New value: +"The record, as a JSON object or a JSON string."decode_receiptexplain_attestation_formatget_public_keyget_review_packget_sample_receiptget_transparency_prooflist_my_receiptsverify_evidence_packverify_receiptworkspace_summaryVerify Attest agreements, stamp codes, receipts, proofs and SHA-256 fingerprints, with no sign-in.
Issue signed receipts for AI agent actions; verify any receipt offline - free, no account.
Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs.
Find governed AI capabilities and verify signed receipts. Read-only, no account.
Add one secure layer between your agents and this server.
