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

Annotations only signal readOnlyHint=true, and the description adds substantial behavioral context: deterministic verdicts, newest-first ordering, keyset pagination on a composite key, the open/resolved lifecycle, persistence of `first_detected_at` across rescans, and `meta.facets` on the first page. This goes well beyond what annotations or the schema alone would tell the agent.

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?

Four dense sentences each contribute distinct information: what the tool returns, ordering/pagination, lifecycle behavior, and differentiation from anomalies. There is no filler or repetition of schema content, and the most identifying facts are front-loaded.

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 tool has 9 optional parameters and no output schema, the description covers the operational essentials: deterministic rule-based results, ordering, pagination key, lifecycle transitions, polling convergence, and first-page facets. An agent has enough context to select the tool, set filters, and interpret pagination without major gaps.

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 100%, so the input schema already fully documents all nine parameters, including defaults, enums, and the `since` polling semantics. The description adds no parameter-specific details but does explain global behavior like facets, which is consistent with the baseline-3 expectation when the schema carries the parameter burden.

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 names a specific verb ('List') and resource ('compliance findings'), then clarifies the domain further as 'deterministic verdicts against the published rules' with explicit ordering and pagination semantics. It also distinguishes itself from `/v1/anomalies`, so an agent can tell it apart from the most similar sibling without reading 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 explicitly contrasts this tool with `/v1/anomalies`, saying anomalies report observed behaviour rather than rule breaches, which is a clear when-not-to-use signal. It does not enumerate all alternative siblings or spell out an exhaustive 'use this when...' statement, but it covers the main routing ambiguity.

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