You cancelled the run — did the work actually stop?
Scored across 3 tools
Each tool targets a distinct step in the cancellation-verification workflow: quoting, submitting a cancellation record, and verifying a receipt. There is no meaningful overlap; an agent can select the correct tool from the purpose alone.
verify_cancel and verify_receipt follow a clear verb_noun pattern, while quote is a shorter standalone verb/noun. The deviation is minor and still readable in context.
Three tools are well-scoped for a narrow cancellation-outcome verification server. Each tool maps to a necessary workflow step without bloat.
The surface covers the full lifecycle: get pricing/quote, submit cancellation to obtain a signed outcome receipt, and verify that receipt's HMAC signature. No obvious dead ends for the stated purpose.
Pricing and exact basket quote (simple_legs + deep_legs priced at the true execution price).
| Name | Required | Description | Default |
|---|---|---|---|
| deep_legs | No | ||
| simple_legs | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral burden. It adds the useful detail that pricing uses the true execution price, but it does not state whether the tool is read-only, what inputs are required, whether it has side effects, or what kind of response to expect.
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 compact sentence with no filler and the key pricing concept is front-loaded. Its brevity is appropriate structurally, even though the content is under-specified for an undocumented schema.
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 two undocumented parameters, no annotations, and no output schema, the description is too thin. It does not explain what the quote returns, what units or format the prices use, or how the integer leg counts affect the basket quote.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and both parameters are undocumented integers. The description repeats the names simple_legs and deep_legs and ties them to pricing, but it does not explain what a leg is, what the integer represents, or how the two parameters interact.
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 that the tool produces a pricing and exact basket quote, and it names the two leg categories being priced. That is enough to distinguish it from the verify_* siblings, though it does not explicitly explain the difference.
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 explicit guidance on when to call this tool, when not to call it, or how it relates to verify_cancel and verify_receipt. The pricing context implies usage, but the agent must infer the conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit a cancel record; returns the signed per-leg cancellation-outcome receipt. One leg = $0.01 verdict; >1 leg = $4.99 full cancel audit (first audit free, one-time trial).
| Name | Required | Description | Default |
|---|---|---|---|
| legs | Yes | ||
| cancel_id | No | ||
| cancel_ts | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses that this is a submit/mutation operation, that it returns a signed receipt, and that pricing depends on leg count with a one-time free trial, but it omits permissions, side effects, idempotency, and what actually happens to the cancel record.
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 definition is compact and front-loaded: the action and return value come first, followed by the relevant cost model. Every sentence adds practical information without waste.
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 three-parameter mutation tool with no annotations, no output schema, and 0% schema description coverage, the description is incomplete. It covers purpose, return type, and pricing but does not explain the nested leg objects, cancel_id, cancel_ts, permissions, or side effects needed to invoke it confidently.
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 the parameters but largely does not. It mentions 'leg' and leg count, giving some meaning to the legs array, but cancel_id, cancel_ts, and the structure of each leg object are left undocumented.
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 action and result: submit a cancel record and return a signed per-leg cancellation-outcome receipt. This is clear enough to understand the tool's core function, though it does not explicitly distinguish it from the sibling verify_receipt.
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 explicit guidance on when to use this tool versus quote or verify_receipt, nor any prerequisites or exclusions. The pricing tiers imply that leg count matters, but they do not tell an agent when this tool is the correct choice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify a receipt's HMAC signature.
| Name | Required | Description | Default |
|---|---|---|---|
| receipt | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full behavioral burden. It indicates an HMAC verification operation but does not disclose return behavior, failure cases, required secrets, or whether the operation is read-only.
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 front-loaded sentence with no wasted words. It is appropriately concise for what it contains.
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?
The tool has a nested input object, no output schema, and no annotations, so the description should do more. It states the core purpose but omits return values, receipt structure, and failure semantics needed to invoke it confidently.
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% for the single required 'receipt' object, which is also nested. The description adds only that the receipt has an HMAC signature, without explaining the receipt structure, signature location, or encoding.
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: 'Verify' a 'receipt's HMAC signature.' It is clear what the tool does, but it does not distinguish this operation from sibling tools such as verify_cancel or quote.
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 explicit guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. Usage is only implied by the tool name and the phrase 'verify a receipt's HMAC signature.'
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.
quote1 field changedInput schema / properties / simple_legsAdded value: +{
+ "type": "integer"
+}quoteverify_cancelverify_receiptCheck your cron jobs, recent runs, workflows and webhooks, and run a job now when you confirm.
Trace events to function runs to the failing step, and bulk-cancel runs.
Resolve whether an uncertain side-effecting action completed before software retries it.
Catch AI agent loops: halt runs that repeat the same failing step or tool call.
Add one secure layer between your agents and this server.