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

Annotations already declare the write/destructive profile, but the description adds real value by clarifying the effect scope: it lands as a draft for review and is not authorized or applied to a bill. It also names the return payload (id, number, sku_url), which no output schema covers. Minor gap: it does not reconcile its benign 'draft' framing with the destructiveHint=true annotation.

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?

Two clauses, zero waste: the action and its draft status are front-loaded, the non-authorization caveat follows, and the return values close it out. Every element earns its place, especially the return payload given there is no output schema.

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?

For a 10-parameter mutation with no output schema, the description covers purpose, the non-applied effect, and return values, while annotations and a 70%-documented schema carry the rest. It is nearly complete; only the destructive/idempotency nuances and a few undocumented parameters are unaddressed.

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 70% and 10 parameters exist; the schema already documents lines, dry_run, credit_date, credit_reason, currency_code, idempotency_key and vendor_credit_number. The description adds no parameter-level meaning (supplier_id, supplier_reference, vendor_credit_note are undocumented in both places), so it sits at the baseline rather than compensating.

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 ('Records a supplier credit memo as a draft vendor credit') with the crucial qualifier that it is a draft, not an authorized or applied credit. It does not explicitly distinguish itself from close siblings such as record_purchase_invoice, 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?

The scenario is implied ('supplier credit memo ... for review'), and the description usefully signals the record is unapplied pending review. However it names no alternative tool or condition for choosing this over record_purchase_invoice or adjust_inventory, and gives no prerequisites (e.g. what must exist first).

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