ausca_get_invocationRead the authoritative durable state, output commitment, and receipt reference for one invocation without creating a new purchase or retry identity.
| Name | Required | Description | Default |
|---|---|---|---|
| invocation_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Output schema / $defs / ArtifactRef / descriptionAdded value: +"Opaque artifact reference minted by artifact commitment. Relay it unchanged; its form is not part of the contract."Output schema / $defs / ArtifactRef / maxLengthAdded value: +512Output schema / $defs / ArtifactRef / minLengthAdded value: +1Output schema / $defs / ArtifactRef / patternRemoved value: -"^runx:artifact:sha256:[a-f0-9]{64}$"Output schema / $defs / ReceiptReference / properties / uri / descriptionAdded value: +"Opaque receipt identity minted by the notary. Relay it unchanged; its form is not part of the contract."Output schema / $defs / ReceiptReference / properties / uri / minLengthPrevious value: -14New value: +1Output schema / $defs / ReceiptReference / properties / uri / patternRemoved value: -"^runx:receipt:.+$"Output schema / $defs / ArtifactEvidenceAdded value: +{
+ "additionalProperties": false,
+ "properties": {
+ "artifact_ref": {
+ "$ref": "#/$defs/ArtifactRef"
+ },
+ "content_digest": {
+ "$ref": "#/$defs/Digest"
+ },
+ "created_at": {
+ "format": "date-time",
+ "type": "string"
+ },
+ "media_type": {
+ "maxLength": 200,
+ "minLength": 1,
+ "type": "string"
+ },
+ "size_bytes": {
+ "maximum": 26214400,
+ "minimum": 1,
+ "type": "integer"
+ }
+ },
+ "required": [
+ "artifact_ref",
+ "content_digest",
+ "media_type",
+ "size_bytes",
+ "created_at"
+ ],
+ "type": "object"
+}Output schema / $defs / ArtifactRefAdded value: +{
+ "pattern": "^runx:artifact:sha256:[a-f0-9]{64}$",
+ "type": "string"
+}Output schema / $defs / InvocationFailureAdded value: +{
+ "additionalProperties": false,
+ "properties": {
+ "code": {
+ "maxLength": 96,
+ "minLength": 1,
+ "type": "string"
+ },
+ "message": {
+ "maxLength": 500,
+ "minLength": 1,
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+}Output schema / $defs / InvocationState / properties / failureAdded value: +{
+ "$ref": "#/$defs/InvocationFailure"
+}Output schema / $defs / InvocationState / properties / output_artifactAdded value: +{
+ "$ref": "#/$defs/ArtifactEvidence"
+}Output schema / $defs / ReceiptReference / properties / public_urlAdded value: +{
+ "description": "Unguessable public verification page for the privacy-bounded hash-only proof. It reveals the receipt digest, service, public price, and completion time, but not input bytes, output bytes, or their content digests.",
+ "format": "uri",
+ "maxLength": 2048,
+ "pattern": "^https://[^?#]+/r/[a-f0-9]{64}$",
+ "type": "string"
+}Output schema / $defs / ReceiptReference / properties / public_urlRemoved value: -{
- "description": "Unguessable public verification page for the privacy-bounded hash-only proof. It reveals the receipt digest, service, public price, and completion time, but not input bytes, output bytes, or their content digests.",
- "format": "uri",
- "maxLength": 2048,
- "pattern": "^https://[^?#]+/r/[a-f0-9]{64}$",
- "type": "string"
-}Output schema / $defs / ReceiptReference / properties / public_urlAdded value: +{
+ "description": "Unguessable public verification page for the privacy-bounded hash-only proof. It reveals the receipt digest, service, public price, and completion time, but not input bytes, output bytes, or their content digests.",
+ "format": "uri",
+ "maxLength": 2048,
+ "pattern": "^https://[^?#]+/r/[a-f0-9]{64}$",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by specifying what is read (durable state, output commitment, receipt reference) and by explicitly stating the operation has no side effects on purchase or retry identity. 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?
One sentence, front-loaded with the core action and resource, and ends with a meaningful exclusion clause. Every word earns its place; no fluff or repetition of the 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?
The tool has a single parameter, a rich output schema (not shown but present), and annotations covering safety and idempotency. The description explains the purpose and side-effect profile sufficiently. It doesn't describe the return value, but the output schema exists, so that burden is shifted. It could mention error cases or when the invocation state might be unavailable, but for a simple read tool this is adequate.
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 carries the burden for parameter semantics. However, the single parameter invocation_id is self-explanatory given the tool name and description, and the schema defines its format (pattern, maxLength). The description doesn't add detail about the parameter, but the parameter is simple and unambiguous. Baseline 3 is appropriate because the description doesn't actively compensate but the parameter is trivially clear from context.
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 ('Read'), a specific resource ('authoritative durable state, output commitment, and receipt reference'), and a clear scope ('for one invocation'). It also distinguishes itself from sibling tools by explicitly noting it does not create a new purchase or retry identity, which separates it from ausca_prepare_invocation and ausca_cancel_invocation.
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 when to use this tool: when you need the authoritative state of an invocation without side effects. It does not explicitly name alternatives or exclusions, but the negative clause ('without creating a new purchase or retry identity') provides clear context that this is a read-only lookup, distinct from preparation or cancellation flows. It lacks an explicit 'use X instead when...' statement, so it doesn't reach a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.