control_evidence

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

readOnlyHint=true is confirmed by the [READ] prefix with no contradiction, and the description goes well beyond it. It explains the populationSize vs sample relationship, when truncated is set, and warns that scanTruncated=true means the population is only a slice and no coverage claim should be made — a genuine correctness caveat an agent could not derive from annotations alone.

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?

Front-loaded with the purpose, then a compact Args list, then return-value semantics — no wasted sentences. The formatting with escaped backticks is a little noisy but each 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?

With no output schema present, the description compensates by naming and interpreting the key return fields (populationSize, sample, truncated, scanTruncated) and their interaction. For a read-only evidence tool this covers everything needed to call it and interpret the result without misleading coverage claims.

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 carries the full burden, and it does: framework enumerates hipaa/pci_dss/soc2/gdpr, control_id gives per-framework examples, since/until are ISO timestamps bounding the period, and sample_size is defined as the number of representative rows. All five parameters gain meaning absent from the schema.

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?

Starts with a bracketed operation mode ([READ]) and states a concrete verb+resource+scope: evidence rows for ONE control, plus population size and a reproducible query. The 'ONE control' scoping makes it distinguishable from broader siblings like query_audit_events or coverage_summary without opening either schema.

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 Args block explains what each parameter means but never says when to reach for this tool instead of query_audit_events, coverage_summary, or generate_evidence_bundle, and states no prerequisites or exclusions. Usage is only faintly implied by the scoping wording, so an agent gets no routing guidance.

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