grc_control_testing

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

Annotations already carry the risk profile (destructiveHint=true, readOnlyHint=false, idempotentHint=false), and the description does not contradict them. The description adds a modest piece of behavioral context: the call executes through the platform's domain-agent dispatcher under the caller's JWT, tenant, and company scope — relevant auth/routing context. However, for a tool flagged destructive, the description never discloses what gets modified, created, or otherwise affected, so the added value over annotations is limited.

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 definition is compact: an action statement, one routing sentence, and two one-line parameter definitions. The Args section is clearly structured and front-loaded, and every line contributes something. The only redundancy is the opening sentence restating the tool's own name, which slightly undercuts the efficiency.

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?

An output schema exists, so return values are covered by structured data, but the definition still leaves the core question unanswered: what does control_testing actually do? It gives no selection criteria versus the many grc_* siblings, no effect disclosure despite destructiveHint=true, and no guidance on what to put in the free-form `message` beyond 'objective.' For a destructive, open-world action with 0% schema coverage, this is materially incomplete.

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 Args section carries the full semantic burden. It does add meaning beyond the schema by distinguishing `message` as a free-text objective from `inputs` as an optional JSON string of structured inputs. But it stops short of describing what structured inputs the action accepts, what a well-formed `inputs` payload looks like, or how the two parameters interact — thin compensation for zero schema descriptions.

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 "Run the grc domain agent action `control_testing`," which is essentially a restatement of the tool name `grc_control_testing` with a verb attached — it falls into the tautology category. The routing sentence adds execution mechanics (dispatcher under JWT, tenant, company scope) but never states what the control_testing action actually accomplishes in the GRC domain. Against a sibling list containing ~10 other grc_* actions, the description does not distinguish this tool's purpose.

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 offers no guidance on when to use this tool versus alternatives such as grc_compliance_audit, grc_sox_audit_package, or grc_risk_register_scan. The routing sentence explains how execution happens (via the domain-agent dispatcher under the caller's scope) but says nothing about the conditions that should make an agent choose control_testing, or any exclusions.

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