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

Annotations already declare readOnlyHint/ idempotent/ non-destructive, and the description adds genuinely new context: it returns an exact preview plus a five-minute confirmation token, other allocations remain untouched, and invoice amounts are unchanged. It still doesn't describe what the preview payload contains or what happens if the token expires, but the value added beyond annotations is substantial.

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, then the constraints and the return behavior in short declarative sentences. Minor redundancy between 'Prepare assigning' and the closing 'it does not apply the change', but nothing is wasted.

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?

No output schema exists, and the description does step in to describe the return value (preview plus a five-minute token). Parameter coverage remains thin, but for a single-argument preview tool with read-only annotations, an agent has enough to call it correctly.

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 0%, so the description must compensate. It explains the load number (trip_number) and the choice between assigning a whole invoice or an exact printed-line index (line_item_index), which is useful, but it says nothing about invoice_id or about how the line index is derived and whether it is zero-based.

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: it prepares the allocation of an invoice (whole or a specific printed line) to a load number, without applying it. The preview-versus-apply distinction from the sibling assign_invoice_load is implied by 'does not apply the change' but the sibling is never named, so the differentiation is inferential rather than explicit.

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?

'Requires confirmation' and the returned token imply this is the step preceding an actual assignment, but the description never says 'call this before assign_invoice_load' or when to skip the preview. Appropriate usage is only implied by the workflow framing.

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