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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), it discloses the crucial async trait: the check runs in the background and returns a workflow ID and Studio URL rather than a result. This is exactly the behavioral context an agent needs and that the annotations do not convey.

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-loaded with the core action, then the async caveat, then parameter guidance. Every sentence adds distinct value with no repetition.

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?

Despite an output schema existing, the description proactively explains the return (workflow ID + Studio URL) and the follow-up tool (GetCheckResults), so the agent knows the full call-and-continue workflow.

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 full burden. It names and explains every parameter: graph ID, variant, subgraph name, proposed schema as SDL, plus optional branch and commit for Studio labeling.

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 states a specific verb (start a schema check) and resource (one proposed subgraph schema against a variant), and anchors it to a known CLI equivalent (`rover subgraph check`). This distinguishes it from the composite-level RunSchemaCheck sibling.

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 routes the agent explicitly to GetCheckResults for reading the outcome, which is strong alternative guidance. It does not explicitly contrast with the sibling RunSchemaCheck or state exclusions, so it falls just short of a 5.

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