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

Annotations only say write, destructive, non-idempotent. The description adds the ownership-proof mechanism (orderId plus the order's billing email), the paid-order requirement, and the downstream workflow — a human editor reviews before publishing. It also flags an operational trap ('a wrong pairing reads exactly like a missing order'), which is behavior an agent could not deduce from annotations or schema.

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?

Five dense sentences, front-loaded with purpose and the ownership rule before the editorial and communication constraints. Every sentence carries a distinct instruction (proof of ownership, payment precondition, human review, client-facing wording, confirm-before-filing) with no filler.

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 destructive, non-idempotent mutation with six parameters and no output schema, the description covers preconditions, the identity check, downstream handling and the messaging constraint. Output shape is not needed since the concerning behaviors are all inbound, and nothing an agent needs to call 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 adds genuine meaning for the orderId/email pair by framing them as a joint ownership proof rather than two independent lookups. It explains the failure mode of a mismatched pair, which the schema does not. The draft, title, authorName and referredBy fields are left to 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?

States a specific verb and resource: filing a client's article draft against a paid order, which is more precise than the name alone. It implicitly separates this from generic siblings like submit_content and submit_campaign_brief by specifying an already-paid order, but it never names an adjacent alternative, so an agent must infer the boundary.

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?

Gives real preconditions: the order must be paid, and the draft text must be confirmed with a human before filing. It also states what not to do (don't claim the piece is published or scheduled). It stops short of naming an alternative tool or the case where a sibling like submit_content should be used instead.

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