compliance-check

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

With no annotations, the description carries the burden well: it discloses that analysis runs against DRAFT policy and recent traffic rather than active policy, that results are heuristic and score-summarised, and that unknown scope labels fail rather than widening. It stops short of stating read-only safety, lookback implications, or result stability/rate behavior, leaving a small gap for an unannotated tool.

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 sentences, front-loaded with what the tool is, then the exclusion/alternative, then the scoping gotcha. No filler and no repetition of schema content.

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?

Four all-optional parameters and no output schema are handled adequately: inputs are documented in the schema, the tool's purpose and limits are described, and the output is characterised as a score. The one remaining gap is what the score response actually contains (per-framework breakdown? findings?), which matters since there is no output schema.

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%, so the baseline is 3, but the description adds real meaning beyond the schema by clarifying the failure mode of app_name/env_name (unknown label = error) and by pointing to the illumio://compliance/* resources for framework guidance. It does not explain how lookback_days interacts with the heuristic scoring beyond the schema text.

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 verb+resource ('check policy posture against a framework'), names the supported frameworks, and describes the mechanism (keyword-routed heuristics on draft policy plus recent traffic) and output shape (a score). It is explicitly differentiated from the sibling collect-compliance-evidence, so an agent can tell them apart 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?

Explicitly positions itself as a 'first look' and states when NOT to use it ('Not audit evidence: for per-test results from ACTIVE policy for an app/env scope use collect-compliance-evidence'), naming the alternative and the selecting condition. It also adds a scoping rule — an unknown app_name/env_name label is an error, not an estate-wide run — which prevents a common misuse.

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