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

Adds genuinely non-obvious behavior beyond the annotations: the account stays in the register, statements survive, and it only leaves net worth from the given day — clarifying what destructiveHint=false means in practice. It also discloses the edge case that a non-zero closing balance is reported rather than refused. Missing: what a re-close does (idempotentHint=false) and whether closure can be reversed.

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 purpose and the guardrail are front-loaded in the first two short paragraphs. The trailing 'Effects: account closed from a day.' restates the opening sentence and adds no information, which is the only waste.

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 no output schema, the note that a non-zero closing balance 'is named in the result' gives the agent a useful hint about the response. Combined with the preservation/net-worth effects, an agent has enough to call it correctly; only idempotency and reversal behavior remain unstated.

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 100% and each of the three parameters is described there, so the baseline is 3. The description adds one real semantic point — that closed_on is the day from which net worth excludes the account — but adds nothing for reason or account_id beyond the schema.

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?

Starts with a specific verb+resource: 'Mark an account closed from a day, with a reason.' That is clearly distinct from the account-editing siblings (purch_update_account, crm_set_account_status). It does not name those siblings explicitly, so it stops short of a 5.

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?

'Only when the person says it is closed' supplies a hard precondition that prevents an agent from closing accounts unprompted — a real usage constraint rather than an implied one. It does not point at the alternative (e.g. purch_update_account for non-closure edits), so no explicit when-not routing.

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