Import Statement

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

With no annotations, the description carries the full burden and succeeds: it states that nothing is created, explains dedup's skip behavior to prevent double-adds, and defines default_split_name fallback semantics. This is strong behavioral disclosure for a non-mutating proposal tool.

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?

The description is dense but well organized: one purpose line, then compact parameter explanations, then the follow-up instruction. Every sentence adds behavioral or workflow value; there is no filler or repetition.

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 proposal-generation tool with an output schema, the description covers input shape, defaults, dedup side effects, required prerequisite, and next step. The only implicit content is the exact proposal structure, but that is covered by the available output schema.

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 0%, but the description manually documents all three parameters in detail: transaction item fields with date format and optional overrides, default_split_name behavior, and dedup matching rules. It fully compensates for the bare 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?

The opening line is specific: 'Turn parsed statement rows into a reviewable import proposal (creates NOTHING).' This names the exact operation and resource, and the parenthetical clearly distinguishes it from mutation tools like confirm_import or create_expense.

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?

The description gives clear workflow context: run sync_all first for dedup, then review the proposal, then call confirm_import. It also explains defaulting behavior for splits. It does not explicitly list alternative tools or say 'do not use create_expense,' but the staged workflow is unmistakable.

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