Run a Workday GraphQL query

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

Beyond the readOnlyHint annotation, the description discloses that the server is read-only, refusing mutation/subscription and type-system documents, and that sensitive fields (SSN, bank account, etc.) are redacted by field name, with aliasing refused. It also notes that operations are unpublished, implying the need for iteration. These details go well beyond the annotations and accurately describe behavior without contradiction.

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 information-dense but each sentence serves a purpose: core function, unique applicability, server restrictions, and redaction behavior. It is front-loaded with the main purpose and the most critical caveats. No redundant or filler content, and it remains structured and readable despite its length.

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?

Given the complexity of a GraphQL tool with variables and output limits, and the absence of an output schema, the description covers the essential operational knowledge: what it does, when to use it, what is rejected, how sensitive data is handled, and the iterative nature. This is sufficient for an agent to invoke it correctly and anticipate behavior.

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 100%, so the schema already documents all four parameters (query, maxBytes, variables, operationName). The description adds minimal parameter-specific detail beyond confirming that query must be a GraphQL query document and that mutations are rejected, which is already in the schema. It doesn't explain syntax or additional constraints, so baseline 3 is appropriate.

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 clearly states the tool's action: 'Run a read-only GraphQL query against Workday's PEX surface' with the specific endpoint, and distinguishes it from siblings by noting it's the only route for Inbox/My Tasks and global search, which lack GET-able .htmld endpoints. This makes the tool's purpose unambiguous and separates it from the other workday tools.

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 states when to use this tool: for surfaces without a GET-able .htmld endpoint (Inbox/My Tasks, global search), and provides exclusions: mutations, subscriptions, and SDL documents are refused. It also warns that operations are unpublished so users must supply the document and expect iteration, giving clear situational guidance.

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