add_expense

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

With no annotations, the description carries the full burden and does disclose real behavior: it mutates the year's expenses tab, rejects duplicates, and blocks writes to filed quarters. It does not cover permissions/auth, error shapes, or what dry_run actually returns, which leaves a gap for a mutation 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?

Three sentences, front-loaded with the effect, then the field list, then the guardrails and dry-run instruction. Every clause carries information an agent needs before calling.

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 mutation tool with no annotations and no output schema, the definition covers effect, field set, and refusal conditions. The remaining gap is the return behavior of dry_run and real runs, which an agent would want before deciding to proceed.

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% and the row object is a free-form nested object, so the description must compensate — and it does by enumerating all sixteen expected keys plus the date format (YYYY-MM-DD). It stops short of explaining the meaning or expected type of opaque keys like fx, business_pct, nif, and code.

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 with scope: 'Add one expense row to the year's expenses tab.' An agent can immediately tell this from add_income or propose_income by the resource named. It doesn't explicitly name a sibling to differentiate against, keeping it just below a 5.

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 prerequisites and workflow: deduplication, refusal on already-filed quarters, and 'Call with dry_run=true first.' That is actionable when-to-use guidance. It lacks an explicit when-not or a pointer to alternative tools for bulk/other cases.

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