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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety behavior is covered by structured data. The description adds genuinely new operational detail: the firm's agent key comes from the client portal's Account tab and must be sent as 'Authorization: Bearer mccf_...'. It also implies per-account scoping (the account's OWN assistant), which bounds what data is visible.

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?

A single dense sentence plus a short credential note, with the audience qualifier front-loaded so an agent can rule itself in or out immediately. The parenthetical 'card per job, or owner-approved net-30' is efficient because it pre-empts a question about term values. Minor cost: the opening noun phrase reads as a label rather than an action, slightly delaying comprehension.

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?

There is no output schema, so the description carries the return-value burden and discharges it by listing the five data points the caller receives. Auth mechanics are also spelled out, which is essential for a credentialed endpoint. It is nearly complete, but it says nothing about failure modes for an unapproved or keyless caller, or about stale/cached balance data.

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?

The tool takes zero parameters, so there is no parameter semantics to document and the baseline of 4 applies. The description correctly adds no spurious parameter talk and instead spends its words on the auth credential, which is the only input the caller must supply outside 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?

The description names a specific resource (an MCC business account) and enumerates exactly what is returned: payment terms, credit limit, open balance, and paused-ordering status. It also scopes the audience to an approved account's own assistant, which separates it from register_firm_account and the firm_invoices/firm_orders siblings. It stops short of an explicit verb such as 'returns' or 'reads', so the retrieval action is implied by the field list rather than stated.

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?

Usage context is implied by 'For an approved MCC business account's own assistant', which tells the agent the account must be approved and the key must belong to that firm. There is no explicit when-not-to-use clause and no sibling is named as an alternative for the unapproved case (register_firm_account exists among the siblings). An agent can infer the right context but must do some of the work itself.

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