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

Annotations only declare readOnly=false, destructive=false, idempotent=false; the description adds genuine behavioral context beyond that — what the link means semantically (the expenses stop counting as personal spending) and the hard invariant that the tied expenses must equal the money in exactly. It does not say what happens if the sums mismatch, nor that the link is reversible via purch_unlink_reimbursement.

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?

The core rule is front-loaded, but the exact-sum constraint is stated twice and the "no longer personal spending" outcome is likewise repeated in the closing Effects line. The phrasing is oddly colloquial ("Tie money in"), which costs a beat of comprehension. It is not bloated, but sentences could be merged without losing meaning.

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 only three fully described parameters, no output schema, and annotations covering the safety profile, the description supplies what's missing: the workflow, the equal-sum invariant, and the post-state. Residual gaps are error behavior on a sum mismatch and the undo path, neither of which blocks a correct call.

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 earns above baseline by adding constraints the schema lacks: the expenses array must sum exactly to in_transaction_id, both are existing purch_transaction ids drawn from a prior purch_reimbursements read, and reason should identify the originating claim. It does not clarify ordering or behavior for a zero/over-amount input.

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 concrete operation: tying an inbound money transaction to the expense transactions it reimburses, and lists the resulting state change (expenses cease to be personal spending). It also names the read-side sibling purch_reimbursements, which orients the agent in the purchases family. It does not name purch_unlink_reimbursement as the inverse, so full sibling 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?

Gives an explicit procedure: read purch_reimbursements, identify the expenses the money covers, confirm the person, then tie with a reason. It also handles the partial-settlement case ("if less came back than was claimed, tie the ones it covers and leave the rest waiting"), which is a real branching decision an agent would otherwise get wrong. No exclusion against adjacent tools like purch_pair_transfer or purch_link_refund is stated.

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