Dependency-probe-gated exit execution with hash-verified extraction and signed receipts.
Scored across 5 tools
Each tool has a distinct action: execute performs the exit, probe checks dependencies, rejoin_check tests re-procurement blocking, sweep is a portfolio operation, and verify_receipt validates signatures. The boundary between probe and rejoin_check (both are pre-flight checks) is the only mild overlap, but descriptions differentiate them.
All five tools share the exit_ prefix followed by a snake_case action/suffix (exit_execute, exit_probe, exit_rejoin_check, exit_sweep, exit_verify_receipt). The pattern is predictable and readable throughout.
Five tools is well-scoped for a focused exit/deprovisioning workflow, with each tool earning its place across the probe-execute-verify lifecycle.
The surface covers the core exit lifecycle (probe, execute, verify, rejoin check, portfolio sweep). Minor gaps remain: no tool to list/inspect past or in-progress exits, nor to cancel an ongoing exit, but these are workable around.
Execute an exit in the proven order; returns the signed receipt. Metered like the HTTP exit (trial/plan rails only via MCP; paid rails use the HTTP endpoint with x402).
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | ||
| service_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden; it does disclose that the call is metered and that it returns a signed receipt, which is useful beyond the schema. It does not state permissions/auth requirements, whether the exit is destructive or irreversible, or what 'proven order' entails.
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 the core action front-loaded and the payment-rail caveat parenthetically contained. Slightly dense but nothing is wasted.
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 2-param tool with no annotations and no output schema, it covers the return value (signed receipt) and billing behavior, which is helpful. It still leaves the 'mode' parameter, auth expectations, and the meaning of the 'proven order' unexplained, so an agent cannot call it fully informed.
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 both parameters, so the description must compensate and largely does not. 'mode' is never mentioned and 'service_id' is only implied by the notion of an exit; 'proven order' might relate to mode but is never explained.
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+resource ('Execute an exit') and adds that it returns a signed receipt, which separates it from exit_probe/exit_sweep/exit_verify_receipt implicitly. However, it never defines what an 'exit' is in this domain and gives no explicit sibling differentiation, and 'in the proven order' is opaque jargon.
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?
Provides a real routing condition: metered like the HTTP exit, with only trial/plan rails available via MCP and paid rails directed to the HTTP endpoint with x402. That is a clear when-not constraint, but it gives no guidance on when to call this versus the sibling exit_* tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Dependency probe: SAFE-TO-EXIT / DEPENDENTS-FOUND.
| Name | Required | Description | Default |
|---|---|---|---|
| service_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, yet it only discloses the two possible result strings. It says nothing about whether probing has side effects, what permissions are required, whether the result is cached, or what happens on error – critical for a tool whose output gates a subsequent destructive exit.
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 extremely short and front-loads the key noun phrase, which is good, but it is telegraphic to the point of under-specification rather than genuinely economical. The two outcome tokens are useful, yet the surrounding sentence fragments omit needed context.
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 workflow tool with no annotations, no output schema, and 0% parameter documentation, the description is far too thin. An agent cannot determine sequencing relative to exit_execute/exit_sweep or interpret the result tokens from this text alone.
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 the description adds no information about service_id – not its format, whether it accepts names or IDs, or whether it can reference multiple services. The parameter name is somewhat self-explanatory, but the description does nothing to compensate for the coverage gap.
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 names a specific verb (probe) and resource (dependencies) and exposes its two outcome states (SAFE-TO-EXIT / DEPENDENTS-FOUND), which hints at its role in an exit workflow. However, it never states plainly what is being probed (service dependents?) or how it relates to the sibling exit_* tools, leaving the agent to infer the purpose from the 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?
There is no when-to-use guidance, no prerequisites, and no routing to alternatives. The agent is not told that this should run before exit_execute, nor how it differs from exit_rejoin_check or exit_verify_receipt, so sibling selection rests entirely on name matching.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check whether a COMPLETE exit receipt blocks re-procuring a service.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | Yes | ||
| service_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. 'Check' implies read-only, but the description says nothing about permissions, side effects, error behavior, or output format, leaving most behavioral traits unstated.
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 single sentence is front-loaded and free of filler, delivering the core purpose immediately. It is perhaps overly terse for a tool with undocumented parameters and no annotations, but structurally 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?
With no output schema, no annotations, and 0% parameter description coverage, the description leaves critical gaps: return values, expected input details, and behavioral constraints are absent. For a two-parameter tool, this is incomplete.
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%, yet the description does not mention either required parameter (service_id, scope). It provides no meaning, format, or expected values for these inputs, failing to compensate for the schema gap.
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 gives a specific verb ('Check') and a precise condition ('whether a COMPLETE exit receipt blocks re-procuring a service'), which distinguishes it from generic receipt verification siblings. It stops short of explicitly naming alternatives or clarifying what a 'COMPLETE exit receipt' entails.
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 call this tool versus siblings like exit_verify_receipt or exit_probe, nor are any prerequisites or conditions for use stated. The agent must infer context entirely from the tool name and purpose phrase.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Portfolio unused-service sweep (Operator plan).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It reveals only a plan-tier requirement; it does not say whether the sweep mutates state, deletes or disables services, is reversible, or what permissions it needs — serious gaps for what sounds like a potentially destructive operation.
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?
It is a single short phrase with no wasted words and the scope is front-loaded, but it is so terse that it is underspecified rather than genuinely concise.
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 annotations, no output schema, and no parameters, the description is the only information source — and it omits what the sweep returns, whether it changes anything, and its relationship to the sibling exit_* tools.
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 takes zero parameters and the schema is empty, so there is nothing for the description to clarify. Baseline of 4 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?
"Portfolio unused-service sweep" names a resource (unused services across a portfolio) and implies an action (sweep), but "sweep" is ambiguous — it could mean identify, report, or remove. Nothing distinguishes it from siblings like exit_probe or exit_execute.
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 parenthetical "(Operator plan)" hints at a precondition, but there is no statement of when to use this tool over exit_probe or exit_execute, nor any exclusion criteria. Usage must be inferred entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify an exit receipt's signature.
| Name | Required | Description | Default |
|---|---|---|---|
| receipt | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and falls short. It does not say whether verification is read-only, what happens on an invalid signature (error vs. false), whether it needs a trusted public key, or whether it verifies only the signature or the full receipt contents.
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?
One short, front-loaded sentence with no filler. It is efficient, though its brevity borders on under-specification rather than true conciseness.
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 nested, undocumented parameter object, no annotations, and no output schema, a six-word description is inadequate. The agent lacks the receipt format, verification semantics, and failure behavior 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?
The single parameter 'receipt' is a nested object with 0% schema description coverage, and the description does not compensate by explaining its expected shape, required fields, or encoding. An agent cannot tell what a valid receipt object looks like.
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 gives a clear verb and resource: verifying the signature on an exit receipt. It is specific enough to distinguish from siblings like exit_execute or exit_sweep, but it never explicitly differentiates itself from them.
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 verify a receipt versus when to execute, probe, rejoin-check, or sweep. No preconditions (e.g., receipt must come from exit_execute) or sequencing relative to sibling tools is stated.
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.
exit_executeexit_probeexit_rejoin_checkexit_sweepexit_verify_receiptCryptographically anchored evidence for agents: verified run receipts, proof-gated settlement.
Governed MCP: agent audit, provenance, deterministic checks, and receipt-backed FragGate execution.
Reviewed public-data search and execution with provenance and verifiable integrity receipts.
Bounded authorization and independently verifiable execution evidence for agents.
Add one secure layer between your agents and this server.
