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

Adds substantial behavior beyond annotations: nothing is filed until confirm is called, the team confirms today's price and sends a quote or pay link, and a signed-in Printdash account is required, with the sign-in fallback described. The return payload (summary to show customer plus confirmation_token) is disclosed. This is exactly the kind of context annotations alone can't carry.

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-loads the eligibility condition, then the action, then the confirm requirement and auth note. Dense but every clause carries information. Slightly long single sentence with chained clauses, but 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?

An output schema exists, so return values need no explanation, and the description still names the key return value (confirmation_token) to signal the two-step flow. Auth requirements, the confirm gate, and the human-in-the-loop pricing step are all covered for what is a non-idempotent, open-world mutation.

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 75%, and the description adds meaning beyond the schema: 'at the same or another quantity' implies the default of keeping the original quantity, and 'optional notes' clarifies intent. It doesn't address item_id, which the schema documents anyway.

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: 'prepares the order page's reorder request' for a job on a past order that Printdash's team priced, with optional quantity change and notes. The eligibility condition ('reorder_by_request in get_order') is precise. It never explicitly contrasts with the sibling `reorder` tool, so the differentiation is incomplete.

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?

Clearly says when this applies (team-priced job on a past order) and what the follow-up step is (confirm after the customer agrees). It gives a clear context but omits an explicit 'use X instead for self-serve reorders' pointing at the `reorder` sibling.

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