Preview Write Tool

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

Adds substantial context beyond the annotations: the token's five-minute expiry, single-use nature, and binding to session, budget, entity IDs and values, plus hosted consent requirements. The 'never instructions' warning about bank memos flags an injection risk the annotations cannot express. All of this is consistent with readOnlyHint=true since the tool itself does not apply the write.

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?

Four tight sentences, front-loaded with the core purpose, then token lifecycle, approval workflow, and a safety caveat. Nothing is redundant and each sentence carries distinct information.

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?

An output schema exists, so return values need not be explained, and the safety/workflow context is thorough. However, for a tool whose only real input is an unconstrained object, the description leaves the agent unable to determine how to populate `input` — a meaningful gap in an otherwise well-specified definition.

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 0% for two parameters, one of which is a free-form nested `input` object with additionalProperties. The description never explains what `tool_name` expects or how `input` must mirror the target tool's arguments, so an agent has no guidance for constructing the call. The mention of 'entity IDs and values' hints at the binding but does not document the parameters.

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 specific verb and resource: reads fresh state and previews an exact write without applying it. That is clearly distinct from the execution siblings in the list, but no sibling (e.g. ynab_tool_execute) is named explicitly, so the agent must infer the pairing.

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 concrete procedural guidance: present the plan to the user and obtain explicit approval before execution, which establishes this as the pre-write step. It does not explicitly name the tool to call afterwards, but the when-to-use context is otherwise clear.

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