Read a Workday task / data card

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

Annotations already declare readOnlyHint/openWorldHint/idempotentHint, so the read-only confirmation is redundant. However, the description adds genuine context: authentication model ('Every request rides your signed-in Workday tab'), SPA URL normalization behavior, and the container/hub delegation semantics for expand. The 'no data is mutated' phrasing mildly re-labels the annotation rather than disclosing something new, but the auth and normalization details carry the score above the baseline.

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 a tight three sentences of prose that front-loads the core purpose and output shape, with each of the following sentences adding distinct value (path construction, then auth/read-only confirmation). The parenthetical list of output fields is dense but scannable. It's near-ideal — the only minor inefficiency is that 'Read-only; no data is mutated' restates the annotation, but this does not meaningfully inflate 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?

For a read-only tool with no output schema, the description carries the burden of explaining return shape, and it does so substantively (title, current user, label/value sections, references, related tasks, export links). Combined with schema documentation for edge cases (expand for hub pages, maxCards capping), an agent has what it needs to invoke this correctly. The absence of caveats around error cases or rate limiting is a minor gap but not critical for an idempotent read operation.

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 100% — all four params (path, depth, expand, maxCards) have rich inline descriptions including examples, defaults, and cross-parameter dependencies (e.g., 'Supplying this implies expand'). The tool description adds value beyond the schema by telling the agent WHERE valid paths come from (prior references or pasted URLs) and implicitly informing value selection when chaining results. This exceeds the baseline of 3 for full schema coverage.

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 opens with a precise verb+resource pairing — 'Fetch a Workday page (task or data card) by its path and return a structured, read-only view' — and enumerates the structured output (title, current user, sections, navigable references, related tasks, export links). This distinguishes it clearly from siblings like workday_fetch (which implies a rawer response) and workday_get_worker_task, while the title reinforces the scope.

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?

The description gives clear context on path provenance ('take it from a prior result's references[].uri or relatedTasks[].uri') and even provides failover guidance (SPA URLs are normalized, container pages need expand). However, it never explicitly names an alternative tool or states when NOT to use this tool in favor of a sibling like workday_fetch, so it stops short of full exclusion guidance.

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