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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description's valuable addition is the data boundary: metadata/approved fields only, with secrets, contacts and original files explicitly excluded — that tells the agent what will and won't appear in the result. It stops short of describing pagination behavior or what 'authorised' requires operationally.

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?

Two short sentences, front-loaded with the action and followed by the data-scope caveat; no filler or repetition. It is efficient, though the brevity leaves real gaps rather than being economically complete.

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?

Annotations and the field-scope sentence cover the read-only profile and output boundaries, and no output schema means return shape need not be explained. However, for a list-style tool with three undocumented parameters and no pagination guidance, the description should say at least how paging and querying behave.

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% across three parameters (limit, query, offset), and the description adds nothing about any of them — not the pagination model, not the default page size, and not what fields the free-text 'query' actually searches. With zero documentation in both places, an agent cannot reliably construct a filtered or paged call.

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 names a specific verb (read) and a specific resource (authorised adp integration status), and the vendor name 'adp' implicitly separates it from the many sibling get_*_integration_status tools (gusto, ukg, paychex, etc.). It does not explicitly route to or defer those siblings, but the vendor qualifier makes the target unambiguous.

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?

There is no statement of when to call this versus the sibling integration-status tools, no prerequisites (e.g. whether the ADP integration must be connected first), and no exclusions. 'Authorised' hints at a permission condition but never states it, so the agent must infer usage entirely.

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