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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description's 'Read-only' is consistent with them. Beyond that it adds real context: sort order (newest first), the exact fields returned including supplier NIF, IVA and the receipt-attached flag, and the single-client scoping. It omits pagination/row-cap behavior, which lives only in the schema.

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?

One front-loaded sentence: audience/account type first, then scope, then ordering, then returned fields. The field enumeration is long but earns its place because there is no output schema.

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 compensates by enumerating returned fields, which is exactly what an agent needs to decide to call it. The remaining gap is row-limit/pagination behavior and whether quarter requires year, both left entirely to the 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 coverage is 75% and already documents link_id provenance and the quarter range, so the baseline is met. The description adds the period semantics ('in a year or quarter') and stresses 'ONE accepted client', reinforcing that link_id is a per-client identifier rather than a tenant scope.

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 the resource (expenses/gastos) and immediately narrows the scope: a gestoría account, ONE accepted client, a year or quarter, newest first. The 'For a gestoría account' and 'ONE accepted client' framing cleanly separates it from list_expenses (own account) and gestoria_facturas_mandante (invoices) without needing to open 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?

'For a gestoría account' and 'ONE accepted client' tell the agent the precondition and the scope constraint that rules out the general list_expenses tool. It does not explicitly name an alternative tool or say when-not to call it, but the account-type gating is a clear, usable condition.

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