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

Annotations already flag destructive/non-idempotent/open-world, but the description adds genuinely new behavioral facts: the change is propagated to the marketplace, it cannot be undone through the API, the call is never retried, and a timeout requires manually checking Channable before retrying. That retry/timeout guidance is exactly what an agent needs for a non-idempotent destructive call.

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 key decision (partial vs full), then constraints, then safety caveats — a sensible priority order with no filler sentences. The raw endpoint path (POST /v1/companies/...) is arguably redundant operational detail, but it is one clause and does not disrupt scanning.

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 three-parameter destructive mutation with no output schema, the description covers scope, per-marketplace limitations, irreversibility, retry/verification behavior, and the buyer-side escape hatch. Nothing an agent needs to invoke this correctly is missing.

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%, so the baseline is 3, but the description goes further by explaining the semantic consequence of order_item_ids — that partial cancellation flips the order into a 'partial' state — which the schema does not convey. Minor gap: no mention of how project_id defaults interact with login context beyond what the schema already says.

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?

Opens with a precise framing ('Seller-side cancellation: set an order to cancelled') that names the verb, resource, and actor scope, and immediately distinguishes partial from whole-order cancellation. An agent can tell exactly what this does and how it differs from siblings like channable_get_order or channable_update_return_status.

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?

Explicitly states when to pass order_item_ids versus omit it, names three marketplaces (Amazon, Cdiscount, Spartoo) that reject partial cancellation, and routes buyer-side cancellations to the marketplace seller account instead. That is when-to-use, when-not-to-use, and alternatives in one paragraph.

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