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

Annotations already declare destructiveHint=true and idempotentHint=false, so the description's added value here is the approval gating: no effect until a human approves in Settings > MCP and execute_approved_action is called, plus the warning that it may cascade to related records. That is substantive behavior an agent cannot infer from annotations. It stops short of saying whether deletion is permanent/irreversible or what exactly cascades.

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 critical safety information (approval gating, cascading) is buried after a boilerplate opener and a redundant restatement of the name. The approval requirement is also stated twice — "configured MCP approval rules" and "MCP approval requirements are configurable by the organization administrator" — which wastes space in a five-sentence description.

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?

Output schema exists, so return values need not be explained, and the approval workflow is covered. However, for a destructive mutation tool the description omits whether the delete is irreversible, what "may cascade" concretely covers, and any state preconditions — gaps an agent needs before invoking it.

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?

There is a single required parameter "id" with 0% schema description coverage, and the description says nothing about it. The agent must infer it is the bid's UUID; the description could have stated that explicitly and noted whether a bid id, approval request id, or similar is expected.

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?

"Delete bid" states a specific verb and resource, so an agent knows exactly what operation is performed. The remaining ambiguity is only relative to siblings (delete_bid_document, delete_bid vs. cancel_bid_approval_request), which the description never addresses — and the opening clause about "RetailHardHat bids records" is boilerplate rather than differentiation.

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?

The description gives an implied usage context ("when working with RetailHardHat bids records in the connected organization") and an important process requirement (human approval, then execute_approved_action), which is genuinely useful. But it never says when NOT to use this versus delete_bid_document or cancel_bid_approval_request, and gives no preconditions such as bid status that would block deletion.

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