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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses numerous behavioral traits: it is deterministic, returns a per-criterion threshold table and canonical citations, surfaces a live verification envelope, and treats 'cannot_determine' as a first-class outcome. It also clarifies the behavior when prior-year data is absent and the implications of group_member forcing 'review'. No contradictions with 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 long but information-dense; every sentence carries essential guidance (coverage, behavior, edge cases). It front-loads the core purpose and determination values first. It could be trimmed slightly without losing key warnings, but given the tool's complexity, the length is justified.

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 tool with multiple jurisdictions, a two-year test, and a verification envelope, the description covers all critical aspects: input requirements, conversion rules, correct handling of missing data, and the meaning of 'cannot_determine'. With an output schema also provided, an agent has everything needed to call and interpret the result correctly.

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?

Even though the schema already describes every parameter (100% coverage), the description adds critical semantics: currency must match the regime and must be converted first (never guessed), prior year is needed for the consecutive-years test and its absence changes the result, and group_member forces 'review'. These enrich the schema meaning substantially.

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 'DETERMINISTIC check of whether a private limited company qualifies for statutory audit exemption' — a specific verb, resource, and outcome. It explicitly names the determination values ('exempt' | 'review' | 'audit_required' | 'cannot_determine') and lists the inputs, making its scope unmistakable and distinct from the audit/deadline/search 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?

The description provides strong usage guidance: it states the covered jurisdictions (MT, GB) and eras, instructs to pass prior_year figures for two-consecutive-years tests, and explains why a missing prior year correctly returns 'review' not 'exempt'. It also warns against overriding with training-data thresholds. It does not explicitly name alternative tools for uncovered scenarios, so it slightly misses the 'when-not' comparison.

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