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

Annotations already flag openWorldHint=true and idempotentHint=true, but the description adds real substance: code may leave the boundary to policy-approved audit models under a configured budget, the call never deploys and never waives a Block, and retries return the existing matching audit. It stops short of stating duration/blocking behavior or whether a Block is produced as a side effect.

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?

Four short sentences, front-loaded with the action, then constraint, then boundary, then retry semantics. Every sentence carries distinct information and nothing is redundant.

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 an all-required-parameter action tool with no output schema, the description covers egress, budget, non-deployment, non-waiver, and idempotency, which covers what an agent needs to decide and call safely. A pointer to how results are later checked would close the remaining gap.

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 75%, so the schema largely documents the four parameters itself (slug-or-id for application, enum with promotion semantics for environmentType, strict UUID pattern for releaseId). The description adds only an indirect hint via 'immutable release'; it contributes no format or selection guidance beyond the schema.

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 gives a specific verb and resource ('Start the company's configured security checks') plus scope ('for an immutable release and environment'), which cleanly separates it from read-oriented siblings like springroll.security.status and springroll.policy.check.

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?

It establishes the trigger condition (an immutable release plus environment needing audit) and rules out adjacent intents with 'Does not deploy or waive Block', plus a retry rule. It does not name a sibling for follow-up (e.g. retrieving audit results via springroll.security.status), so routing to alternatives is only implicit.

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