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

No annotations are provided, so the description carries full burden. It discloses the return values (verdict and correct value), the fact that unknown keys are rejected (not silently dropped), and implies that without 'asOf', the law as of today is used. This is sufficient for safe invocation.

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 very concise: two sentences and a usage note. Every sentence adds value, and the critical placement rule is front-loaded. No redundant or vague phrasing.

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 complexity (3 params, nested objects, 14 siblings), the description covers purpose, usage, parameter semantics, and behavioral constraints. It lacks details on error handling or invalid facts, but overall is sufficient for an agent to use the tool 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?

Schema coverage is 100%, baseline 3. The description adds meaning beyond schema: explains that 'facts' can be flat IDs or group objects, notes 'negative = refund' for claimedAmount, and gives default toleranceDollars=1. It also clarifies that 'asOf' and 'target' must be inside facts, enhancing parameter understanding.

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 clearly states the tool's function: 'Verify a claimed tax amount against the law.' It explicitly specifies the return values ('verified' or 'refuted' with correct value) and distinguishes itself from sibling tools like verify_fact by targeting tax claims specifically. The scope (yours, a user's, or another tool's) is also clarified.

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 explicitly advises: 'Use this as a self-check before presenting any tax number,' providing clear context. It also gives critical placement instructions for 'asOf' and 'target' inside the facts object. However, it does not explicitly state when not to use this tool or compare it to alternatives like verify_fact.

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