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.