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

With annotations declaring a non-read-only, non-idempotent, non-destructive write, the description adds genuine context beyond them: the org-admin authorization requirement and the governance rule that MCP approval requirements are admin-configurable while business workflow approvals always apply. It omits duplicate-handling behavior, which matters given idempotentHint=false.

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?

Three short sentences with the disambiguating clause front-loaded. The final sentence about MCP vs business workflow approvals is slightly abstract but earns its place as governance context.

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?

An output schema exists, so return values needn't be explained, and authorization is covered. However, for a nested-object mutation with non-idempotent semantics at 0% parameter coverage, the description leaves the agent guessing about field meaning and re-adding an existing approver.

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% and the single 'data' parameter is a nested object with four undocumented fields (userId, approvalOrder, isRequired, dealId). The description says nothing about any of them — no meaning for approvalOrder ordering, no note that dealId is optional scoping, no userIdentifier semantics — so it compensates zero for the coverage gap.

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 the action ('Configure a budget approver') and immediately contrasts it with the sibling it is most likely confused with ('not an approval decision', i.e. decide_budget_approval_request/submit_budget_approval_request). It does not differentiate from list/remove/reorder_budget_approver, but the core resource and non-purpose are explicit.

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?

'not an approval decision' is an explicit when-not-to-use against the approval-decision family, and 'Organization admin required' states a hard prerequisite. It stops short of naming the adjacent configuration siblings (reorder_budget_approver, remove_budget_approver), so routing is clear but not fully enumerated.

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