create_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 well: it discloses the two-phase preview/commit semantics via confirm=true, the default-equal-split fallback, and the sum constraint on exact_amounts. It still omits permission/auth requirements and whether a preview returns a stable identifier for a later commit.

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 confirm/preview rule, then a scannable bulleted split block, then an Args section. Slightly verbose and mixes prose and PyDoc-style Args, but every section carries non-redundant 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?

For an 11-parameter mutation tool with no annotations and no output schema, the description covers the critical unknowns: confirmation gating, split mutual exclusivity, and the exact_amounts sum invariant. What it lacks is any statement about the preview's return shape and what errors to expect on a mismatched sum.

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%, so the description must compensate, and it does: it defines acting_as, description, amount (positive, tricount currency), paid_by, tricount, category (with a full enum listing plus free-text fallback), expense_date format and default, plus the three split strategies. This is nearly a complete parameter glossary.

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+resource ('Crea un gasto en un tricount') and immediately distinguishes behavior from siblings by disclosing the preview-by-default semantics ('Sin confirm=true solo devuelve una vista previa'). An agent can tell this apart from list_expenses or create_reimbursement 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?

Explicitly explains the default no-split behavior ('si no se da ninguna, se reparte en partes iguales entre todos los miembros') and enumerates three mutually exclusive ways to define the split. It does not, however, state when to prefer exact_amounts over ratios, nor does it reference siblings for related flows.

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