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

Annotations already declare non-destructive, non-read-only, open-world behavior. The description adds critical context beyond annotations: the check runs in the background, returns a workflow ID and Studio URL rather than a result, and requires a handoff to GetCheckResults. This fully discloses the async workflow.

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?

The description is four tight sentences, front-loaded with the core action and followed by alternatives, operational behavior, and parameter guidance. Every sentence adds necessary information without padding.

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 async check-start tool with an output schema, the description covers when to use it, what it returns, how to retrieve results, and all parameter roles. Nothing required to call it correctly is missing.

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 must carry the full burden. It does: it maps the three required parameters (graph ID, variant, proposed schema as SDL) and two optional ones (branch and commit to label the run in Studio), making parameter meaning clear despite the empty 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 states a specific action (start a schema check) on a specific resource (proposed schema against a variant) and explicitly distinguishes it from RunSubgraphCheck. An agent can immediately identify what the tool does without opening the schema.

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 explicitly names when to use this tool (monograph or whole supergraph schema) and when to use the alternative (RunSubgraphCheck for one subgraph). It also clarifies the follow-up tool GetCheckResults, leaving no ambiguity about routing.

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