OpenArg — Argentina public data

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

Annotations already declare readOnly/idempotent/openWorld/destructive=false, so safety is covered. The description adds genuinely useful behavior beyond that: the exact fields returned and the quota note ('No descuenta preguntas'), which tells the agent this call is cheap to repeat.

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-loads what the tool does, then return shape, then per-parameter meaning. Dense but every sentence earns its place; no filler.

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 3-parameter search tool with an output schema and fully annotated safety profile, the description covers purpose, return fields, all parameters, and routing to siblings. An agent has everything needed to invoke it 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 0%, so the description must carry all three parameters — and it does: `texto` with concrete Spanish examples, `portal` with its filtering role and referent tool, and `limite` with its 1–25 range. Nothing material is left undocumented.

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 (catálogo de OpenArg) with a concrete scope ('más de 30.000 datasets de portales oficiales'). An agent can immediately tell this is a search-over-catalog tool and it is differentiated from siblings like describir_tabla/obtener_datos, which it names as the downstream consumers of results.

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?

Routes the agent explicitly: results' tables should be used with `describir_tabla` and `obtener_datos`, and `portal` filtering is done via `listar_fuentes`. Clear when-to-use context, though it never states a when-not-to-use condition.

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/openWorld/non-destructive, so the safety profile is covered. The description adds genuinely new behavior: it consumes 1 of the user's 10 monthly questions (a quota/rate-limit disclosure) and returns source links, data-quality warnings, and remaining-question count. It does not state idempotency or failure behavior, so it stops short of a 5.

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 purpose, then examples, then return contents, then the quota/routing caveat — a sensible ordering. The four examples are somewhat redundant with each other but each demonstrates a distinct question shape, so the length is defensible rather than padded.

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?

An output schema exists, yet the description still usefully previews that responses include datasets with official links, coverage warnings, and remaining quota. For a one-parameter, open-world query tool with sibling routing already resolved, nothing an agent needs to call it correctly 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 0% for the single 'pregunta' parameter, so the description must carry the burden — and it does via four sample questions that establish that input is a free-form natural-language question (Spanish) rather than a structured query. It never states format constraints or length, which keeps it from 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 ('responde una pregunta sobre datos públicos oficiales de Argentina, con fuentes') and the four example questions pin down the exact kind of input it handles. It also explicitly separates itself from the sibling pair buscar_datasets + obtener_datos, so an agent can route between them 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?

Gives a concrete routing rule with a cost trade-off: 'si podés responder con buscar_datasets + obtener_datos, preferí esas', which implies this tool is the fallback when the raw-fetch siblings cannot synthesize an answer. Both the alternative and the selecting condition are named.

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 and openWorld. The description adds genuinely useful non-schema behavior: it enumerates what is returned and notes "No descuenta preguntas" (does not consume quota), which the annotations do not cover. Not fully exhaustive, but valuable context beyond structured fields.

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 is returned, followed by input provenance and usage ordering. Three short lines, no filler, everything 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?

An output schema exists, so return values need not be explained, yet the description still summarizes them, and it documents the one undocumented parameter and the call ordering. Adequate for a simple one-param read tool; only minor edge cases (matching rules, error behavior) are unaddressed.

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% for the single parameter, so the description must compensate, and it does: it explains that `tabla` is the name returned by buscar_datasets. It does not specify case sensitivity or exact matching rules, but the origin/format meaning is conveyed.

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 plus concrete outputs (columnas con tipo, cantidad de filas, período cubierto, muestra). It also names which sibling produces its input (buscar_datasets) and which it precedes (obtener_datos), so an agent can place it in the workflow 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?

"Usalo antes de obtener_datos para saber qué columnas pedir y qué fechas existen" gives explicit ordering and rationale, and it clarifies where `tabla` comes from. It stops short of stating when not to use it or naming a competing alternative, but the sequencing guidance is clear.

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, idempotentHint, and destructiveHint=false. The description adds meaningful behavioral context beyond those annotations: it clarifies that the call does not consume questions and counts as a data-mode request, which helps an agent reason about quota impact.

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 description is two short sentences with no waste. The core purpose is front-loaded, and the quota note follows as a secondary operational detail.

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 the tool's simplicity, zero parameters, available output schema, and rich annotations, the description is nearly complete. It explains what is listed and adds quota context, though it could better position itself relative to sibling tools.

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?

The tool takes zero parameters, so there are no parameter semantics for the description to explain. The baseline for a no-parameter tool is 4, and the description does not need to compensate for any schema gap.

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 clear verb and resource: lists the open data portals covered by OpenArg and how many datasets each has. It is specific about what the tool returns, but it does not distinguish itself from sibling tools such as buscar_datasets or consultar_datos_publicos.

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?

The description does not say when to use this tool versus alternatives. The second sentence mentions quota behavior ('No descuenta preguntas: cuenta como un pedido del modo datos'), but that is not usage guidance for selecting this tool over its siblings.

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 establish that this is a read-only, idempotent, non-destructive operation. The description adds useful behavioral context beyond annotations: CSV output, official source, filter limit of 5, row limit of 1–500, and the fact that it does not consume questions.

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 description is front-loaded with the core action and then uses a compact bullet list for parameter semantics. Every line adds useful information without redundant repetition.

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 an output schema present, the description does not need to explain return values, and it covers most operational details for a 7-parameter tool. The main gap is the lack of explicit routing against sibling tools, but the parameter and output-format context is sufficient 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 description coverage is 0%, so the description must carry parameter meaning, and it largely does: column names, date formats, exact-match filters with an example, sort direction, and row limits. It does not fully document the required tabla parameter or all defaults, but it compensates well for the missing schema descriptions.

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 fetches rows from a table in CSV format from the official source. This clearly identifies the tool’s function, though it does not explicitly distinguish it from sibling tools such as consultar_datos_publicos.

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 operation description and by the reference to describir_tabla for exact column names. However, there is no explicit guidance on when to use this tool versus alternatives like consultar_datos_publicos or buscar_datasets.

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