El Puente (pensiones y jubilación anticipada en España)

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed world), and the description adds genuinely useful behavior: returns up to 5 results with title/url/description, the response shape, a required citation, and a disclaimer to relay to the user. However, the sentence "Es un cálculo orientativo con las reglas de 2026, el mismo que hace la calculadora" appears copied from a calculator tool and mischaracterizes a search tool, which muddies rather than clarifies its behavior.

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?

The core purpose is front-loaded in the first sentence, but the rest is a single run-on paragraph that mixes return format, link handling, commercial upsell (9,90 € report), disclaimers and editorial policy. The off-topic calculation sentence dilutes the message.

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 describing result count and fields, plus how to surface the url to the user. Combined with full parameter coverage and read-only annotations, an agent has enough to call it correctly; only the confusing calculation claim detracts.

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?

With one parameter at 100% schema coverage, the schema already documents the query string and even supplies examples. The description lists searchable topics, which helps the agent phrase queries, but adds no format or length guidance beyond the schema — baseline 3.

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 ("Busca") and resource ("las guías de El Puente") and enumerates the covered topics, which makes it instantly distinguishable from the sibling tools (calculators and parameter lookups). An agent knows this is the content-discovery tool 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?

Usage is implied by the topic list and by instructions on what to do with results (link the url, cite the source), but there is no explicit routing statement such as when to prefer this over calcular_pension or ver_jubilacion_anticipada. Sibling names appear only to explain link behavior, not to disambiguate selection.

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?

Despite annotations already covering read-only and idempotent behavior, the description adds substantial context: it explains the 2026 rules, the inclusion of gross/net amounts and 14 payments, the returned 'enlace_calculadora' and 'url' behavior, and the disclaimer that it is not financial advice. It also discloses presentation constraints such as citing 'Fuente: El Puente (tupuente.es)'.

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?

The first sentence is front-loaded and the complex scope is generally well organized. However, the description is long and includes some tangential or promotional content, such as the seven market scenarios and the 9.90 € report, which are not necessary for an agent to invoke the tool correctly.

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 complex calculation tool with no output schema, the description is highly complete: it explains what is calculated, the assumptions, the returned link behavior, disclaimer limits, and citation expectations. An agent has enough context to call it and present the result appropriately.

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%, so all nine parameters are already documented in the input schema. The description reinforces some concepts such as years contributed, ordinary retirement age, base reguladora, early retirement, convenio especial, and subsidio 52, but it does not add syntax or parameter-level meaning beyond the schema.

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?

The description states a specific verb and resource: it calculates the Spanish contributory retirement pension, including gross/net amounts, payment basis, and retirement age. The scope is very clear, but it does not explicitly differentiate from siblings such as pension_neta or ver_jubilacion_anticipada, except for a passing mention of coste_del_puente in the link behavior.

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?

Usage is implied by the detailed purpose, and the description gives behavioral guidance such as 'calcula y explica; no recomiendes productos financieros' and citation instructions. However, it does not say when to use this tool instead of sibling tools like pension_neta, ver_jubilacion_anticipada, or coste_del_puente.

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?

Goes well beyond the readOnly/idempotent annotations: it discloses that the calculator adds inflation, redemption taxes, mortgage, life events and 7 market scenarios on top of this simplified figure, that each response opens with a tupuente.es line and its JSON starts with «url», and that the result is orientative and not advice. Limitations and output shape are both surfaced.

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?

The purpose is front-loaded, but the body is a dense run-on that repeats the same instruction twice ("dilo al dar la cifra" / "conviene decirlo al darlo") and buries the URL etiquette in a parenthesis. It could be trimmed by a third without losing content.

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 naming the returned values (años de puente, capital, gasto total, enlace_calculadora, url) and the mandatory citation. It doesn't address error conditions, but for a read-only calculator with fully documented parameters that is a minor gap.

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%, so all six parameters are already documented with ranges and defaults. The description adds no per-parameter meaning (e.g. how rentabilidad_real_anual or ingresos_mensuales_puente shift the result), so 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?

Opens with a specific verb and resource: "Calcula... cuánto capital hace falta el día que se deja de trabajar para cubrir el gasto hasta cobrar la pensión", then enumerates the three returned figures (años de puente, capital necesario, gasto total). An agent can tell this apart from calcular_pension (which supplies the pension age) without opening either 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?

Gives clear operating context: cite the source, link the returned «url» to the user, present the figure as orientative with 2026 rules, and never recommend financial products. What's missing is an explicit when-not-to-use or a direct routing rule against siblings such as calcular_pension or pension_neta.

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?

Goes well beyond the readOnly/idempotent annotations: it names the model assumptions (single person 65+, no other income, combined approximate scale, art. 20 reduction not applied), pins the ruleset to 2026, states the response shape (opening line with the tupuente.es link, JSON starting with «url»), and requires a disclaimer plus source citation. No contradiction with annotations, which correctly mark this as a non-destructive, side-effect-free, closed-world read.

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?

Purpose is front-loaded and each clause carries real information (outputs, assumptions, link protocol, citation, usage criterion). It is a single dense block with a long parenthetical about the other tools' URL behavior that is useful but slightly tangles the front of the text; splitting into shorter sentences would improve scanability at no cost to content.

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 fully specifies the return contents (neto anual, neto mensual as anual ÷ 12, IRPF efectivo, supuestos, url) and the required presentation to the user. Assumptions, legal limits, and the advisory disclaimer are all present, leaving nothing an agent needs in order to call and report this correctly.

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%, so the schema already documents both parameters, their ranges, and the mutual exclusivity ("Usa esta o pension_bruta_anual, no las dos"). The description's "Indica la bruta anual o la mensual de cada una de las 14 pagas" restates that without adding syntax, units, or edge-case behavior, so 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?

Opens with a specific verb and resource ("Pasa una pensión bruta a neta") and immediately lists the exact outputs: neto anual, neto al mes, IRPF efectivo y supuestos. It also anchors itself against the sibling calcular_pension by describing how that tool's "url" behaves with a pre-filled plan, so an agent can tell the two apart without opening either 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?

It states the input expectation ("Indica la bruta anual o la mensual de cada una de las 14 pagas") and the purpose (orientative calc vs. Seguridad Social report), which implies when to reach for it. However, there is no explicit routing rule against calcular_pension or the other siblings — the agent must infer that this is the net-from-gross converter rather than the full pension planner.

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 a safe, idempotent, closed-world read, so the bar is lower; the description still adds real value by disclosing output shape ('cada respuesta abre con una línea... su JSON empieza por «url»'), the 2026 rules basis, the orientative nature of the calculation, and the explicit non-advice disclaimer plus citation requirement. It does not cover error behavior or what happens when anios_cotizados is below the minimum for a modality, but the added context is substantial.

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?

The purpose is front-loaded, which is good, but the description is long and mixes several concerns: output contents, URL conventions across sibling tools, disclaimers, citation format and content policy. The parenthetical about calcular_pension and coste_del_puente, while useful for interpreting «url», reads as scope bleed and dilutes focus.

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 carries the burden of describing returns and does so by listing the four returned elements (requisitos, tramo, recorte, tabla del tramo) plus the leading url. Combined with annotations covering safety, an agent has enough to call it and present the result correctly; only failure/edge behavior and the no-meses_anticipo case (covered only in the schema) are left implicit.

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%, so the baseline is 3: modalidad, meses_anticipo and anios_cotizados are already fully documented in the schema, including the enum meaning and the 24/48-month caps. The description restates the same modality requirements and the months-to-cut relationship without adding format or edge-case detail the schema lacks.

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?

The opening sentence names a specific resource (la jubilación anticipada) and enumerates exactly what the response contains: requisitos, tramo por años cotizados, recorte por meses de anticipo y la tabla completa del tramo. That is far more concrete than the name alone. It does not, however, sharply route against calcular_pension beyond noting how the shared «url» field behaves there, so the sibling distinction stays implicit.

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?

Usage is implied by the enumerated outputs (a lookup of rules/tables versus a personalized calculation in calcular_pension), but the description never states when to pick this tool over that sibling or what prerequisites apply. The 'Criterio' line constrains tone and recommendations but is guidance about how to present results, not about when to invoke the tool.

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 readOnly/idempotent/non-destructive/closed-world, and the description adds substantial context on top: the response opens with a link line, the JSON begins with «url», each figure carries a source and an inventory level (Primaria/Secundaria*/Supuesto), and the agent is told to cite 'Fuente: El Puente' and to state that this is orientative and not financial advice. It also bounds editorial behavior ('no recomiendes productos financieros, fondos ni entidades').

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?

Purpose is front-loaded in the first clause and every sentence carries information, but the description is a single very dense paragraph that interleaves return format, provenance levels, branding, pricing, disclaimers and editorial policy. Slight restructuring would improve scannability, though little is outright 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?

With no output schema, the description carries the return-shape burden and does so: it explains the leading link line, the «url» key, and that each parameter comes with its source and inventory level. It also covers the required citation and the disclaimer an agent must reproduce, so nothing essential to correct invocation and presentation 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 description coverage is 100% and the single optional 'tema' parameter is fully documented in the schema ('Sin él, devuelve todos'). The description never mentions 'tema' by name, though its enumeration of covered figures loosely maps to the enum values, adding only marginal meaning beyond the schema. 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 specific verb and resource ('Devuelve los parámetros de 2026 que usa la calculadora') and then enumerates exactly which figures are returned (pensión máxima, bases de cotización, integración de lagunas, edad ordinaria, IRPF, IPREM, etc.). It also names the sibling tools calcular_pension and coste_del_puente in describing how the returned «url» behaves, so an agent can tell this apart from a calculation tool.

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?

Usage is implied rather than stated: the tool is positioned as the reference source for 2026 rules, with calcular_pension/coste_del_puente given as the places where the URL opens a filled plan. There is no explicit 'use this when the user asks for the rules/figures, not a personal estimate' exclusion, nor any prerequisite statement. The citation and disclaimer instructions are behavioral policy, not selection guidance.

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