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

Annotations already declare a non-read-only, non-destructive mutation; the description goes further with an explicit 'Effects' line (both rows reviewed as one transfer, move counted once between the two accounts) and the refusal condition on mismatched amounts. It stops short of saying whether the pairing is reversible or pointing at purch_unpair_transfer as the undo, which would complete the disclosure.

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 definition, then prerequisites, then the exception, then effects — a sensible order. Some sentences are wordier than needed ('a savings account kept elsewhere, an owner draw' parenthetical, the slightly tangled 'into the card' example), 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?

No output schema, so the description carries the return burden via the 'Effects' sentence. For a 3-param mutation with annotations already covering safety flags, it supplies everything needed: preconditions, the upstream discovery tool, the edge-case routing, and the resulting state change.

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 semantics the schema does not: the two ids must be exactly opposite in amount and belong to different accounts, and that they represent paired movement between the caller's own accounts. The 'reason' parameter's purpose ('show the person... pair with a reason') is contextualized even though its schema description already exists.

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?

Opens with a specific verb and resource: 'Tie the two sides of one move between your own accounts: the row where money left and the row where it arrived.' This is unmistakably distinct from purch_transfers (suggestions), purch_review_transaction (single-row review), and purch_unpair_transfer (the inverse operation). The accounting consequence ('counted once, as neither spending nor income') further pins down intent.

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?

Explicit workflow: read purch_transfers for suggested pairs, show the person, then pair with a reason. Preconditions are stated as hard rules ('amounts must be exactly opposite and the accounts different; a pair is refused otherwise'). It also names the case where this tool is the WRONG choice — an account with no statements here is not a pair and should be handled as a transfer row naming the destination.

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