Get Verification Report

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

With no annotations provided, the description fully carries the behavioral transparency burden, and it does so impressively. It discloses a real side effect: a stale cached verdict automatically triggers a background re-evaluation on this read, so the agent knows a second call is needed for the refreshed result. It also clarifies the semantics of `misaligned_assertion_ids` as a directive rather than evidence, and explains how drift items behave, all of which goes far beyond what the input schema alone conveys.

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 front-loaded with a clean summary sentence and then organized with bullet lists for the `sufficiency` block and drift items, which makes a complex output easy to read. A small redundancy exists around `stale` (status value plus boolean shortcut), and the overall length is long, but every sentence contributes to the needed semantics. This is well-structured and not overly padded.

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?

The tool is reasonably complex with six parameters and a detailed output structure, but the description goes deep into the crucial parts of the output: the meaning of each per-control status value, the handling of `misaligned_assertion_ids`, and the effect of drift. Since an output schema exists, it does not need to spell out every return field. A modest gap is the unstated purpose of `server_version` and the exact tier1/tier2 distinction, so it is not a perfect 5.

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 83%, so the input schema already documents the parameters (`limit`, `offset`, `status`, `model_id`, `summary_only`, `server_version`). With that high baseline, the description is not expected to compensate heavily, and it mostly restates the `summary_only` default instead of adding new semantics to the parameters. Therefore a baseline 3 is appropriate.

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 a specific verb-resource pair: 'Get verification report with summary stats and sufficiency gaps' and goes on to list the concrete contents (tier1/tier2 counts, per-control verification status, sufficiency details). This makes the tool's purpose clear enough to distinguish it from many siblings like get_review_queue or get_controls. However, it never names or contrasts a specific sibling alternative, so it stops short of the explicit differentiation that earns a 5.

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 implies the tool is meant for retrieving verification reports and explains how to control the output volume ('By default returns summary only... Set summary_only=False to include full assertion details'). It also gives a narrow operational hint to call again after a stale result. Yet it does not explicitly say when to choose this over similar tools such as get_sufficiency or check_control_gaps, and never provides a when-not-to-use or alternative recommendation.

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