RCO-A2A - Regulatory Compliance Objects

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context: superseded records are returned and retained byte-identical. This goes beyond what annotations alone provide.

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 sentence with no filler and front-loads the core purpose. The phrase 'the audit trail, retained byte-identical' is slightly awkward but still compact and informative.

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, read-only, idempotent getter with an output schema and a precise record_id pattern, the description covers the essential behavior including the superseded-record nuance. Domain terms like RCO and audit trail are not expanded, but the schema and simple scope make this 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?

The description adds minimal meaning beyond the input schema, simply stating that the parameter is a record_id identifying an RCO. Schema description coverage is 0%, but the detailed pattern in the schema already defines the expected format thoroughly, compensating for the missing parameter description.

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uses a specific verb ('Return'), names the resource ('RCO by record_id'), and adds a distinguishing detail ('including superseded records'). This clearly differentiates it from sibling tools like list_issuers, publish_record, and resolve_compliance.

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 intended use is implied by the phrase 'by record_id', but the description never states when to choose this tool over alternatives or when not to use it. There is no explicit guidance about sibling tools, so the agent must infer usage context from the tool name and description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the operation as read-only, idempotent, and non-destructive. The description adds that the result is signed and returned verbatim from a fixed URL, which is useful context but not a substantial behavioral disclosure 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?

A single sentence conveys the action, the exact resource, the signed/verbatim nature, and the source URL without any filler. Every clause contributes meaningful information.

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 parameterless, read-only tool with a full output schema and strong annotations, this description is sufficient. An agent knows what will be returned, where it comes from, and that no input is required.

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, so there is no input semantics for the description to clarify. The baseline of 4 applies because no parameter information is needed.

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 resource (the signed consortium issuer registry document) and the action (Return), along with the canonical source URL. It does not explicitly contrast with sibling list_rule_sets, but the resource is specific enough to avoid confusion.

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 use this tool versus siblings like list_rule_sets, get_record, or resolve_compliance. The description states what is returned but not under what conditions an agent should select this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint=false. The description adds value beyond annotations by specifying the temporal scope ('in force and formerly in force'), the response fields, and the explicit exclusion of regulation text. It gives a clear behavioral contract for a list operation without contradicting 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 is two compact sentences with no filler. The core purpose is front-loaded, and the negative boundary is stated immediately after. Every word contributes to scope or behavioral expectations.

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 required enum parameter and an output schema, so return structure is already covered. The description supplies the missing semantic context: what a rule set is, which temporal versions are included, and what is explicitly not returned. This is sufficient 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 description coverage is 0%, and the only parameter, jurisdiction, is merely referred to as 'for a jurisdiction' in the description. This adds little beyond the schema's enum. However, the parameter name and enum values are reasonably self-explanatory, so the tool remains callable, though special values like 'apex' are not 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?

The description uses a specific verb-resource pair: 'List the versioned rule sets in force and formerly in force for a jurisdiction' and enumerates the exact fields returned. The negative clause 'Never the regulation text' further disambiguates it from other tools. It clearly distinguishes itself from siblings like list_issuers and get_record by content and scope.

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 the tool: whenever an agent needs versioned rule set metadata for a jurisdiction. However, it does not explicitly contrast this with siblings such as list_issuers or resolve_compliance, nor does it state 'use this instead of...'. The 'Never the regulation text' clause is a boundary on output, not usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

It discloses important behavioral traits beyond the idempotentHint annotation: GSC never authors records or holds partner keys, records are never modified after submission, verification and Azure Confidential Ledger receipting are performed, republishing byte-identical records returns the same receipt, and errors are typed. This gives an agent a strong model of side effects and guarantees.

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 front-loaded with purpose, then acceptance criteria, then behavior, then idempotency and error behavior. Every sentence earns its place, and there is no redundant padding or restatement 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?

Given the complex one-parameter schema and existing annotations, the description covers preconditions, verification requirements, side effects, idempotency, and error behavior. The presence of an output schema means return-value detail is not required here. No significant decision-relevant context is missing.

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 schema has 0% description coverage for the single `record` parameter, so the description must carry semantic weight. It does: it explains that the record must be schema-valid RCO v1.3, that the issuer must be active in the signed consortium registry, that `verification_url` must match the registered JWKS URL, that the detached JWS must verify, and that `record_id` and supersession must be consistent. These are meaningful constraints not obvious from the raw schema alone.

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 opens with a precise verb and target: 'Publish a signed Regulatory Compliance Object to the partner rail (rco-a2a-cpg.ai).' It further calls this 'The ONLY write path in the suite,' which clearly differentiates it from the sibling read/resolve tools.

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 states when to use this tool: for publishing/writing, and uniquely in this suite. It implicitly routes non-write operations to siblings by labeling itself the only write path, though it does not explicitly name the alternative tools or state when not to use it beyond that.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

This description goes well beyond the annotations by disclosing determinism, the pre-resolved signed CPG-404 fallback inside the universe, the typed record_not_found error outside it, and the fact that nothing is signed at request time. These details give an agent concrete expectations about outcomes and side effects beyond the readOnly/idempotent/closed-world hints already present.

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 compact, front-loaded, and every sentence adds a distinct behavioral fact. A small deduction is warranted because it relies on unexplained domain jargon such as "SPEC v1.2 pairs.json," "jurisdiction doors," and "CPG-404," which increases cognitive load despite the tight structure.

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 closed-world complexity, two required parameters, annotations covering safety, and an existing output schema, the description is complete: it covers success behavior, fallback records, error behavior, determinism, and the absence of request-time signing. Nothing necessary for an agent to call or interpret the tool is missing, even though the domain vocabulary is assumed.

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 description ties both parameters to the operation: object_id identifies the object and jurisdiction selects the jurisdiction, and it clarifies that unknown objects inside the resolved universe are handled. But with 0% schema description coverage, it does not elaborate on allowed object_id forms, jurisdiction-door semantics, or special envelope values like apex; the schema's pattern and enum carry most of the parameter-level burden.

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: "Return the current signed Regulatory Compliance Object for an object in a jurisdiction." It also distinguishes itself from generic record retrieval by emphasizing signed, deterministic compliance resolution and closing with "Never narrative." This makes the tool's purpose unmistakable even among the sibling tools.

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 clear context for when the tool is relevant — resolving compliance state for an object in a jurisdiction — and defines boundary conditions via the resolved universe and the record_not_found error. However, it does not explicitly name sibling tools or state when to prefer resolve_compliance over get_record or other alternatives, so usage routing is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.