Decide work item

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

With no annotations, the description carries the full burden and does well: it discloses the pre-write validation read, the refusal conditions, that the decision executes as the authenticated user, that the result reports case, recorded outcome and acting identity, and that mismatched userName/roleName aborts the call. Gaps remain — the "write gate" is named but never explained, and it does not say whether an already-recorded decision can be reversed or re-submitted.

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 purpose before behavior, and nearly every sentence carries operational content. The trailing sentence about naming people, roles and requests by display names rather than OIDs sits awkwardly against the earlier instruction that userName/roleName must be midPoint names, which reads as mildly inconsistent and costs a point.

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 six-parameter mutation tool with an output schema, the definition covers preconditions, refusal behavior, execution identity, and return contents. An agent has everything needed to decide whether to call it and what arguments to supply, with the display-name/OID tension being the only minor ambiguity.

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%, so the baseline is 3; the description earns above that by specifying that userName and roleName are the midPoint unique-name attribute (a login, not a display name) of the objects the OIDs reference, and that a mismatch causes refusal. That adds cross-parameter semantics the schema alone does not convey, though it does not clarify the accepted values of decision or comment conventions.

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?

States a specific verb pair and resource: "Approve or reject an open approval work item assigned to the authenticated user, with an optional comment." The scope qualifiers (open, assigned to the authenticated user) plus the pointer to list_work_items and claim_work_item let an agent separate this from the sibling read and claim tools immediately.

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?

Gives an explicit precondition sequence: the tool reads the case as the user before writing, and it refuses work items that are not open or not in the approval inbox (routing to list_work_items). It also names a concrete exclusion case with its alternative — a group-offered item nobody has claimed must be claimed first via claim_work_item.

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