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

With no annotations present, the description carries the full burden and does most of it: it declares the operation is side-effect-free ('Nothing is spent or held') and enumerates the return shape. It omits auth/credential requirements and any indication of what the decision trace contains or how costly the call is.

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?

Three terse sentences, front-loaded with the most decision-relevant fact ('Dry run'), with zero filler. 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?

For a 9-parameter tool with no output schema, the description usefully covers the return value (decision enum, rule, full decision trace) and the non-mutating guarantee, which is the essential behavior. The gap is routing guidance versus the sibling payment/rules tools.

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 89%, so the schema already documents nearly every parameter in detail — the local_hour text even explains its dry-run-only semantics and contrast with pink.request_payment. The description adds no parameter meaning beyond that, so the baseline 3 applies.

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?

States a specific operation (dry-run policy evaluation) and the exact outcome vocabulary: would_allow / would_ask / would_block, plus the rule and decision trace. 'Nothing is spent or held' separates it from pink.request_payment, though it never names that sibling outright.

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?

'Dry run' implies the when-to-use context (preview a decision before committing), but the description never explicitly says to call this before pink.request_payment or when to reach for it over pink.list_rules. Usage must be inferred rather than read.

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