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

Annotations only flag destructive=true and idempotent=false; the description goes well beyond that by disclosing the concrete side effects (credit note raised and applied, invoice.status -> paid) and by insisting the act is visible and reasoned rather than silent. This tells an agent exactly what state changes to expect, which annotations alone cannot convey.

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?

Front-loaded with the core action and mechanism in the first two sentences, with effects spelled out at the end. Mostly tight, though the aphoristic 'the threshold ... is yours to police; the record that it happened is not' is stylistic filler an agent does not need.

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 'Effects' line usefully substitutes for a return-value description. The notable gap is that the tool is non-idempotent and destructive, yet the description never warns against retrying, which risks duplicate write-off credit notes.

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% for both parameters, so the schema already defines invoice_id and reason fully. The description adds only indirect meaning — that the reason becomes a visible, audited record — without format, length, or validation detail beyond the schema. Baseline 3 applies.

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 (write off an uncollectible invoice balance) and immediately clarifies the mechanism: a credit note of kind write_off raised and applied to the invoice. It distinguishes itself from deletion/void ('never a deletion'), which implicitly separates it from siblings like o2c_void_invoice and o2c_create_credit_note, though those tools are never named.

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 trigger condition is clear — an uncollectible open invoice balance — but there is no explicit routing against alternatives (void_invoice, close_short, create_credit_note) or stated preconditions such as invoice state or approval threshold. The line about who may write off how much being 'yours to police' explicitly defers policy rather than guiding tool selection.

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