control_audit

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the mutating-but-not-destructive framing is already carried; the description adds genuinely new behavior: resume reuses the persisted checkpoint instead of duplicating the crawl, cancel stops plugin work, and pause/control is only native where the plugin owns the crawl. It does not state reversibility or permission requirements, but the added operational caveats are substantive.

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 tight sentences, front-loaded with the action set and then the non-obvious semantics. Every sentence adds information; none restates the enum or name.

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?

For a two-parameter, no-output-schema control tool, the definition covers what each action does and the important edge case (pause only where the plugin owns the crawl). Return/result behavior after cancel or resume is unstated, but the core invocation-relevant context is present.

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 burden. It explains the semantics of the action values (especially resume's checkpoint reconciliation and cancel's effect on plugin work), but says nothing about auditId beyond what the UUID format/pattern already implies, leaving one of two parameters undocumented.

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 set of verbs (pause, resume, cancel) against a specific resource (an audit job), so the agent immediately knows this is lifecycle control rather than the sibling query tools like audit_status or list_audits. It is cleanly distinguishable from start_audit, which the actions do not overlap.

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?

Gives real guidance on each action: resume reconciles the persisted checkpoint rather than launching a duplicate crawl, and native pause/control applies only where the plugin owns the crawl. It does not explicitly route the agent between this tool and siblings (e.g. use audit_status to check state first), so it falls short of full when/when-not guidance.

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