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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds value beyond them by guaranteeing the call will never trigger or restart a scan — the single most important behavioral caveat for a status endpoint — and by naming which findings are returned redacted.

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?

Two tight sentences with no filler; the returned fields are front-loaded and the negative constraint follows as a closing guardrail. Nothing could be removed without losing information.

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?

With no output schema in place, the description correctly compensates by enumerating the returned data. Combined with a two-parameter, read-only signature, the definition gives an agent enough to invoke it correctly; only the provenance of auditId is left unstated.

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 50%: the 'context' parameter is fully documented in the schema while 'auditId' has only a type and UUID pattern. The description does not explain where the auditId comes from or what it identifies, but the name plus UUID format makes its meaning largely self-evident, so the gap is minor rather than blocking.

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 concrete verb and resource combination plus the exact payload returned: job status, policy decision, redacted findings, unchecked controls. It implicitly distinguishes itself from springroll.security.audit via 'never starts or retries a scanner', though it never names that sibling outright.

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?

'Read the current job status...' establishes the use context (polling/checking an existing audit) and 'Never starts or retries a scanner' rules out the starting/retry case, pointing the agent toward the audit tool. There is no explicit prerequisite such as 'requires an existing auditId from springroll.security.audit', so the routing is implied rather than spelled out.

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