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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: server-owned fields cannot be touched, and the call may be gated by organization-configurable MCP approvals plus mandatory business workflow approvals. It stops short of saying whether the update is a partial merge or a full replace of the field definition.

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 compact sentences with the operational constraint front-loaded and no filler. The second sentence about approval configuration is somewhat generic boilerplate, but it is short and carries real gating information.

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?

This is a destructive mutation with a nested, entirely undocumented payload and an output schema that excuses explaining return values. The description leaves the most consequential questions unanswered — which fields of 'data' to supply, whether omitted fields are cleared, and how the id relates to the target record — so it is not sufficient for correct invocation.

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%, so the description carries the full burden, yet it mentions no parameter at all. The nested 'data' object exposes nine undocumented sub-properties (label, tabId, fieldKey, helpText, metadata, fieldType, sortOrder, isRequired, defaultValue) with no explanation of semantics or which are required for an edit versus left untouched.

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 ('Configure/edit') against a specific resource ('diligence_field'), which implicitly contrasts with create_diligence_field and delete_diligence_field in the sibling list. It does not explicitly name any sibling alternative, so distinguishing relies on the reader's knowledge of the rest of the family.

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?

'Server-owned fields are excluded' gives one real precondition and thus a partial when-not rule. However, there is no explicit guidance on when to use this versus create_diligence_field or update_diligence_tab, and no mention of what a caller should do instead for excluded server-owned fields.

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