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

With no annotations provided, the description carries the full burden. It discloses useful behavioral context: the tool returns a compliance judgement, blocker list, missing-facts list, and next actions, which implies it handles incomplete inputs gracefully rather than erroring. However, it does not disclose side-effect profile (read-only vs. mutating), authorization requirements, or behavior when required inputs are unsatisfiable — gaps that matter for a decision tool.

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 sentences with zero waste. The scoping statement is front-loaded with the key discriminator (single-premises, single-authority), and the second sentence is a compact exclusion list. For a tool of this complexity, the description is remarkably tight and every clause earns its place.

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?

This is a high-complexity tool: 56 parameters, no output schema, and no annotations. The description covers purpose and output categories well, but an agent invoking it correctly still lacks the return value shape, side-effect profile, and any guidance on which authority-specific parameter sets apply to a given authority value. The routing story is complete; the invocation story is substantially under-specified.

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% across 56 parameters, so the description must compensate, and it does not. It adds no meaning about authority, applicant_age, applicant_age, venue_type, or any of the authority-specific fields. The only marginal connection is that 'single-authority' implies the authority parameter selects the jurisdiction. The schema's titles and enums are self-descriptive, but for a 56-parameter tool the agent receives no guidance on which parameters matter for which authority or how the decision engine consumes them.

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 scope ('ACTUAL SINGLE-PREMISES, SINGLE-AUTHORITY licensing compliance decision') and enumerates concrete outputs: compliance verdict, regulatory/local-policy blockers, missing decision facts, and next actions. The explicit 'Do NOT use for...' list differentiates it from sibling tools by function, so an agent can tell it apart from preflight_readiness, compare_licensing_requirements, and local_policy_capabilities without opening their schemas.

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 clearly states when to use the tool ('Select for...') and gives explicit exclusions: general service/pricing information, input-readiness checks, cross-authority comparison, and policy-capability coverage. It does not literally name the sibling tool to switch to for each excluded case, but the exclusions map directly to the functions of preflight_readiness, compare_licensing_requirements, premises_licence_info, and local_policy_capabilities, so routing is nearly explicit.

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