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

Goes well beyond the annotations: 'An agent may submit but never decide', a human approver is required, an agent cannot approve its own request, and it creates review work for named people. It also clarifies that PRODUCTION_PROMOTION does not deploy, which is exactly the kind of side-effect transparency that prevents misuse of a mutation 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?

Front-loads the core constraint (submit but never decide) and the confirm-with-user warning, then organizes type-specific behavior into scannable bullets. Length is justified by eight request types and eight parameters; every sentence carries actionable 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?

For a mutation tool with no output schema and a nested payload object, the description covers the missing pieces: what the call produces (review work, not a deployment), the human-approval gate, and the follow-up call to springroll.deploy.promote. Nothing an agent needs to call it correctly is absent.

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?

Despite 88% schema coverage, the description adds conditional, cross-parameter semantics the schema cannot express: defaults for releaseId and targetEnvironmentType, which types require justification, that UAT_PROMOTION requires targetEnvironmentType, and that the ROLLBACK deployment goes in payload.targetDeploymentId defaulting to the last successful one.

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 and resource ('Submits an approval request') and enumerates all eight supported request types, so the agent knows exactly what it creates. It is clearly distinguishable from siblings like springroll.approval.get and springroll.deploy.promote.

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 states when to use it versus the alternative ('this does NOT deploy... Once approved, call springroll.deploy.promote'), and gives a hard usage constraint plus a prerequisite ('Confirm with the user before calling this'). Decision rules are spelled out per request type rather than left to inference.

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