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

Goes well beyond the annotations by disclosing cascade behavior ('and its dependent records'), the absence of a force override, and a mandatory human-in-the-loop gate requiring approval in Settings > MCP plus a call to execute_approved_action. It also notes that org-configured MCP approvals and business workflow approvals both apply, which materially changes how an agent should plan the call.

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 operation and its cascade are front-loaded in the second sentence, and the approval flow follows logically. The opening sentence ('Use this when working with RetailHardHat budgets records in the connected organization') is generic filler that earns little, keeping this just short of a 5.

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 one-parameter destructive tool with an output schema and destructiveHint already declared, the description covers the essential unknowns: cascade scope, no force override, and the required approval round-trip. It omits what happens if the budget is not a draft (error vs. silent no-op), which is the one remaining gap an agent might need.

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% for the single budgetId parameter, so the schema supplies only type/format. The description implicitly constrains the ID to reference a draft budget, which adds real meaning, but it does not explicitly identify budgetId as the target or clarify where the UUID comes from.

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 and resource with a meaningful qualifier: 'Delete a draft budget and its dependent records,' which distinguishes it from the numerous sibling delete_* tools and from update_budget. It never names an alternative tool, but the 'draft budget' scope makes the operation 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?

'No force override' and the draft-only framing imply that non-draft budgets cannot be removed with this tool, which is useful usage context. However, it never states what to do instead for a non-draft budget (e.g. submit_budget_for_approval) or which siblings handle budget categories, line items, or templates.

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