propose_reclassification

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

With no annotations, the description carries full burden and succeeds: it explicitly says 'Nothing is written', enumerates the validation checks, discloses the derived-E09 refusal rule, and clarifies that admissible: true means well-formed/permitted, not correct. This is rich behavioral context beyond the schema.

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 the core purpose, then proceeds through side-effect, validation, refusal, and verdict semantics, finally routing to the sibling. Each sentence adds distinct information; the only mildly explanatory backstory ('which is the rule that stopped a model...') earns its place by making the refusal rule meaningful.

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 five required parameters, zero schema descriptions, and no annotations, the description is nearly complete: it covers side effects, validation constraints, verdict meaning, and the next action. It falls just short only in not clarifying run_id's role and leaving evidence string format to inference.

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 compensate. It adds meaning for code (must resolve and be assignable), hypothesis (must exist), evidence (must cite a record the exception names), and exception_id (via the exception's label), but run_id is never explained. This is substantial but incomplete compensation.

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 specific verb and object — 'Ask whether a proposed code for an exception would be admissible' — and immediately distinguishes itself from the write path by noting 'Nothing is written' and pointing to accept_classification as the action that makes the proposal real. This leaves no ambiguity about what the tool does or how it differs from its siblings.

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?

It states the tool is a non-mutating check and tells the agent the follow-up operation: 'Making it so is accept_classification', which writes under the credential. It also names when the proposal will be refused (e.g., derived E09 outranks it), giving concrete selection and exclusion criteria.

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