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

The description is unusually candid about side effects: 'manual vendor rules stay unchanged; otherwise its learned vendor rule/counter is updated', plus the 5-minute token expiry and the explicit no-refresh/no-push/no-payment scope. But 'counter is updated' describes a state mutation on a tool annotated readOnlyHint=true and idempotentHint=true, which conflicts with both hints and is exactly the kind of detail an agent must know before calling.

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 core preview/token/no-apply information is stated, but the middle sentence packs vendor-rule inheritance into the same block as scope exclusions, producing a dense run-on. The most decision-relevant fact (does not apply the change) sits at the very end instead of being front-loaded.

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 description usefully explains what comes back (an exact preview plus a five-minute confirmation token) and enumerates what is not triggered. The remaining gap is input shape, which is unaddressed at 0% schema coverage, but for a single-parameter preview tool the overall picture is close to sufficient.

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%, so the schema alone does not explain the nested PostingAccount fields (provider enum, invoice_id UUID, account_id). The description gestures at the domain ('active account', 'cached chart', supplier/account names from saved records) but never clarifies which inputs identify the invoice vs. the account, so it only partly compensates for the gap.

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 states a specific operation on a specific resource ('Prepare choosing an active account from this workspace's cached chart') and closes with 'it does not apply the change', which signals preview semantics. It never names the sibling set_invoice_posting_account as the applying counterpart, and the opening phrasing is roundabout rather than a direct 'preview setting the invoice posting account'.

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?

It implies the workflow by stating 'Requires confirmation' and returning a five-minute confirmation token that does not apply the change, and it scopes out provider refresh, bill push and payment. However, it never explicitly says to call set_invoice_posting_account (or get_invoice_posting_preview) in which circumstances, leaving the agent to infer the follow-up tool from the token mention.

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