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

Beyond the annotations it discloses the dedupe rule ('the same vendor and number is refused a second time'), the approval lifecycle, and the preservation rule ('Never invent a number or a date; empty beats guessed'). It closes with an explicit effects statement. These are behaviors an agent could not infer from readOnlyHint=false/idempotentHint=false alone.

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 purpose, then extraction guidance, then workflow routing. Slightly long and the closing 'Effects: bill recorded, waiting for approval' restates the earlier approval sentence, but no sentence is 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?

With 12 params, no output schema, and mutation annotations, the description covers what to extract, what happens on success, duplicate handling, and who approves next. It stops short of saying how to recover from a rejected duplicate or what the created bill's identifier looks like, which matters without an output schema.

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 already 100%, so the baseline is 3; the description adds genuine guidance on how to fill fields — vendor name 'as a person would say it', amount and currency 'as printed', category 'in the person's words', and bill date vs due date vs terms_days. That is more than restating 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?

Specific verb and resource: 'Record a bill a vendor sent: who, their number, the dates, the amount,' and it explicitly bounds scope with 'nothing is paid from here.' It does not, however, address the near-identical sibling p2p_record_vendor_bill (PO-matched vendor bills), leaving an agent to guess between the two.

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 an explicit triggering situation ('You were handed a vendor's invoice (a PDF, a photo, an email)') and rules out the wrong expectation ('nothing is paid from here'), pointing to purch_approve_bill for approval, the bank for payment, and purch_payables for cash-against-due.

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