Suggest categories for pending transactions

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

Goes well beyond the readOnly/openWorld/idempotent annotations: discloses that it issues three YNAB requests (transactions, categories, accounts), that off-budget/tracking accounts can never be pending, that `categories` arrives on the first page only, that amounts are currency units with negatives for spending, and warns that payee/memo are untrusted bank text to be treated as data. This is exactly the extra context annotations cannot 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-loaded with the core action, then progressively adds usage, cost, and edge-case guidance. It is dense and slightly long, but nearly every sentence carries actionable information (the prompt-injection warning and the null-suggestion branch in particular), so little 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?

Given an output schema exists, the description need not explain return values, yet it still clarifies the fields an agent must reason about (`suggestion`, `categories`, `possible_transfer_with`). Combined with the read-cost and safety notes, nothing an agent needs to invoke it correctly is missing.

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 100%, so the baseline is 3; the description adds genuinely useful semantics by explaining that `categories` is only returned with the first page, which gives the `cursor`/pagination parameters operational meaning beyond their schema text. Limit/cursor mechanics themselves still come from 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+resource: 'List the transactions waiting for a category, with a suggestion when history allows.' It is clearly distinguishable from siblings like find_transactions (all transactions) and from the mutating apply_categories, and it states the scope of the read (whole plan, pending/unclassified only).

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?

Explicitly routes usage: 'Use this first when asked to classify or tidy up transactions,' and names the follow-up tool ('assign with apply_categories'). It also gives branch guidance for edge cases: what to do when `suggestion` is null (choose from `categories` or ask the user) and when `possible_transfer_with` is present (suggest linking instead).

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