Delete transaction

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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds material context the agent would otherwise not have: the delete mutates books and account balances, it requires human confirmation, it is rejected for source-owned records, and it depends on an unofficial web-app API whose session can expire with a concrete remediation command. That is exactly the beyond-annotation disclosure this dimension rewards.

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 action and the destructive warning, then the failure modes, then the auth remedy — a sensible order with little wasted wording. The embedded container hostname and login command are verbose but actionable; the sentence could be tightened 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 no output schema, the description should cover behavior and side effects, and it does: mutation of books and balances, rejection paths, and auth prerequisites. The only real omission is what a successful call yields (no returned record, for instance), which an agent deleting an entity would reasonably want to know.

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 67%: businessId and expectedSequence are documented in the schema, while id is a bare string but self-evident. The description contributes nothing about expectedSequence, an optimistic-concurrency guard whose purpose (failing when the transaction changed since it was read) is worth reinforcing for a destructive call. Baseline 3 fits since the schema does most of the work.

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?

The first clause states a specific verb and resource ("Delete a transaction") and pins the semantics to the web app's own Delete behavior. An agent can immediately distinguish it from the many read/update siblings such as wave_get_transaction and wave_update_transaction without opening a 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?

It gives clear context: confirm with the user first, and expect a refusal for transactions that must be removed at their source (invoice payments, payroll). It also tells the agent what to do when the web session is missing or expired. It stops short of naming an alternative action for the refused cases (for example reversing via wave_update_transaction or deleting the source record instead), leaving that to inference.

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