Tournride — Camino de Santiago bike rental

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 that prices are computed by the reservation engine (bike days + outbound transport + return transport + active promos like Early Bird), that it returns MTB/E-bike/Gravel categories, and that concrete models arrive in available_models. It also warns against estimating or caching prices, a meaningful behavioral constraint. It stops short of stating the operation is read-only or what permissions it needs.

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 core verb and returned value, then a short imperative block. Mostly economical, though the second paragraph repeats the 'ask the client' theme and the exact-price emphasis already made in the opening.

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?

No output schema exists, so the description must carry return-value context, and it does name the key field (available_models) plus the bike categories and price composition. Combined with 100% schema coverage for the six params, an agent has enough to call it, though output shape is only partially described.

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 100% and the schema already embeds rich per-parameter instructions (altura, puntoInicio, puntoFin, seleccion). The description adds no syntax or format detail beyond that, so the baseline 3 applies; its parameter-related content is generic 'ask the client' guidance.

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 (Consulta) and resource (disponibilidad bicicletas) scoped to Camino de Santiago routes, and enumerates the returned value (real-time availability, exact prices, sizes, bike categories). It does not explicitly distinguish itself from the sibling crear_presupuesto_alquiler_camino, despite overlapping on pricing, so an agent must infer the read-vs-create split.

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?

Offers operational guidance ('pregunta al cliente lo que pide cada parámetro', 'usa SOLO los precios que devuelve la tool'), which steers invocation behavior. However, it never states when to call this tool versus the sibling budget tool, nor any exclusions, so tool selection is left implicit.

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

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that a real persistent record is created (not a simulation), that the tool does not estimate or recalculate, that size selection is deferred to the client via the link, that only the returned amounts and validity should be trusted, and what to do if no link is returned. This is exactly the side-effect and trust-boundary context an agent needs.

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 what the tool does, then prerequisites, then constraints. Every sentence is functional and no filler is present, though at five short paragraphs it is longer than strictly necessary and could be tightened slightly without losing meaning.

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?

Despite having no output schema and no annotations, the description covers the return contract (link or no link), the fallback when no link is produced, the trust boundary on returned amounts and validity, and the deferred size selection. Nothing an agent needs to call this correctly and handle its result is missing.

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 already 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it clarifies that size is deliberately NOT a parameter here (resolved by the client later), that idioma is the conversation language rather than the trip country, and that transport is computed by municipality. It stops short of explaining the seleccion basket's exact shape beyond the schema, so not a 5.

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 ('Guarda la cotización como PRESUPUESTO'), the concrete output (a link the client opens to pick size and formalize), and distinguishes it from its only sibling by naming the consultar_disponibilidad tool and what this one does not do (no estimation, no recalculation). An agent can tell exactly what this produces without opening the 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?

Explicit prerequisites ('Llama ANTES a consultar_disponibilidad_bicicletas_camino: de ahí salen los model_id y el precio exacto'), an explicit activation condition ('solo cuando el cliente ya ha elegido modelos y unidades'), and an explicit when-not framing ('crea un registro real, no una simulación'). It also handles the no-link fallback path, so the routing decision is fully specified.

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