Dipromotions — catálogo y presupuestos

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered; the description then adds genuinely new behavior: a failed search returns suggested categories and sections instead of an empty list, and each product carries `masterCode`, starting price and detail URL. It does not disclose result volume, pagination defaults or whether the filters can be combined, which is the remaining behavioral gap.

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?

Four sentences, front-loaded with the no-argument behavior and then the argument modes; almost every clause carries information. The `outlet` definition (

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 5-parameter read-only search with no output schema and 100% schema coverage, the description is close to complete: it explains return contents (code, price-from, URL) and the no-results behavior. The one substantive omission is filter-combination semantics (categoria vs seccion vs q), which matters for correct invocation.

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 100%, so the baseline is 3 and the schema already documents all five parameters including the enum meanings. The description still adds semantic value by framing `q` as an all-catalog text search that overrides the listing modes and by clarifying the empty-result fallback. It is silent on whether `q`, `categoria` and `seccion` compose or are mutually exclusive, leaving that ambiguity unresolved.

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 resource (a customizable promotional-articles catalog) plus every mode of access: no arguments for categories/sections, `categoria`, `seccion` and `q` for the different listings. An agent can immediately tell this is the discovery/browse tool and distinguish it from calcular_precio and pedir_presupuesto, which are transactional.

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 explicit when-to-use routing for each argument combination, which is exactly what a multi-mode search tool needs ('Sin argumentos devuelve las categorías'; 'con `categoria` lista los productos'; 'con `q` busca por texto en todo el catálogo'). It stops short of naming the sibling tools, so it never says to switch to calcular_precio for pricing or pedir_presupuesto to order — an agent could plausibly try to resolve prices here since 'precio desde' is mentioned.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description reinforces this with an explicit no-side-effects statement ('no crea ninguna solicitud ni avisa a nadie'). It also discloses the key caveat that the result is orientativo and excludes finish, color and transport costs — real behavioral context beyond the annotations, though nothing on auth, limits or output format.

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?

Four short sentences, front-loaded with what is returned, then equivalence to the web table, then the no-side-effects guarantee, then the caveat. No filler; each sentence earns its place.

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, and the description compensates by enumerating the return components (unit without customization, unit with marking, totals, published tiers). Combined with the read-only annotation and full schema coverage, an agent has enough to call it correctly, though the exact response shape is only described in prose.

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 documents masterCode, quantity (with the 25-unit minimum) and positions. The description adds only indirect meaning, linking 'unitario con marcaje' to the marking parameter. With the schema doing the heavy lifting, the baseline 3 applies.

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 precise verb and resource (calcular precio orientativo) plus the scope: unit price without customization, unit price with marking, totals and published tiers, for a catalog product at a given quantity. It also separates itself from pedir_presupuesto by declaring it creates no solicitud, so an agent can distinguish it from siblings without opening schemas.

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?

Explains the context of use (same calculation as the price table on the product page) and implicitly routes quoting/ordering intent elsewhere by stating 'No crea ninguna solicitud ni avisa a nadie'. It also warns that the definitive amount depends on finish, color and shipping, which tells the agent when the figure is not binding. It never names a sibling explicitly as an alternative.

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?

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, but the description adds what those hints cannot: a request is persisted, a real salesperson replies to that email, and the turnaround is under 24 business hours. It also discloses the confirmation-before-send duty, which is meaningful behavioral context for an outbound, non-idempotent action.

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 tight sentences, front-loaded with the action and the response promise, followed by the guardrails. The 'no inventes ningún correo' rule slightly duplicates the email field's schema description, a minor redundancy rather than waste.

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?

Given seven parameters, no output schema and present annotations, the description covers prerequisites, side effects and timing well. The only gap is it does not say what comes back to the agent on success (a confirmation or reference), which for a non-idempotent submission tool would be useful to know.

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 100%, so the schema already defines all seven fields and the baseline would be 3. The description adds a semantic constraint on the key parameter beyond the schema text: the email must belong to the interested person and must never be invented, reinforcing that optional fields (phone, company) are only for data the person supplied.

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 and effect: it sends a real quote request to the Dipromotions sales team, with a stated response time under 24 business hours. The 'real send to a human' nature distinguishes it implicitly from the read-only siblings buscar_catalogo and calcular_precio, so an agent knows this is the terminal action of the three.

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 preconditions: only use data the person actually gave, and read back what will be sent before submitting. It also states a hard constraint ('el correo tiene que ser de la persona interesada; no inventes ninguno'), which is a clear when-not-to guidance rather than a vague hint.

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