Edit transaction

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

Annotations already declare destructiveHint=true and idempotentHint=true; the description goes beyond them with the optimistic-concurrency behavior (reads first and sends the current sequence, so it never overwrites a newer edit), the destructive detail that unlisted lines are removed, and the web-session auth requirement including the exact recovery command. It does not describe the response payload, but the concurrency and removal semantics are the material behavioral facts.

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-loads the purpose and then walks through the three transaction shapes efficiently; nearly every sentence carries an actionable constraint. It is a dense single paragraph that would scan better as short bullets, and the environment-specific login line is verbose, but nothing is truly redundant.

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?

For a 16-parameter destructive mutation with no output schema, the description covers the gaps that matter: authentication/session recovery, concurrency safety, dry-run preview, confirmation policy, line-removal semantics, and the journal-entry balancing invariant. An agent could call this correctly without further research.

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?

With 81% schema coverage the schema already documents most fields, but the description adds cross-parameter meaning the schema cannot: which parameter bundle applies to single-category vs split vs journal-entry transactions, that line amounts include sales tax and must sum to the total, and that omitting `order` adds a line. A few parameters (businessId, verified, expectedSequence) get no elaboration beyond the schema, so it falls short of a 5.

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+resource ('Edit a transaction as in the Wave web app') and enumerates exactly what is editable (date, description, notes, reviewed, account, amount, category, vendor/customer, split lines). It is trivially distinguishable from wave_create_transaction and wave_delete_transaction without opening any schema.

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 explicit mode routing: single-category transactions use categoryId/vendorId/customerId/amount/salesTax, split transactions pass `lines`, and journal entries have no bank side and must keep debits equal to credits. It also names alternatives and preconditions (use wave_get_transaction for line order, dryRun to preview, confirm with the user before changing amounts or accounts).

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