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

The description says it 'Delete's a row, but annotations declare destructiveHint=false (additive-updates only). An agent trusting the annotation would assume nothing is destroyed, while the text says a row is removed. This is a direct conflict, though the added owner-check, cost, and API-key context is otherwise useful.

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 dense clauses with no filler; the verb+resource is front-loaded before the differentiation, and the operational notes (cost, auth) are correctly demoted to the tail.

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?

With annotations and an output schema present, the description covers the remaining agent-critical facts: ownership check, cost, API-key requirement, and scope versus a contact delete. The only completeness gap is that its destructive framing conflicts with the annotation, leaving safety ambiguous.

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 67%: request_id and idempotency_key are documented in the schema, while account_id is not. The description compensates partially by naming account_id as the row identifier, but adds no format or source detail for it.

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 ('Delete one person_accounts row by account id') and explicitly scopes it against a nearby operation ('not a reviewed contact delete'), so an agent can separate it from delete_person without opening either schema.

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 parenthetical 'not a reviewed contact delete' gives a clear use-context and implicitly routes the agent elsewhere for a reviewed contact removal, and 'owner-checked' signals the precondition. It stops short of naming the alternative tool or stating an explicit when-not rule.

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