Agents Colombia

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

With no annotations supplied, the description must carry the behavioral load. It does disclose two genuine traits: the listing is free of charge ('gratis') and prices are denominated in USD. However, it says nothing about whether the operation is read-only, whether results are paginated or filtered, or how large the catalog may be.

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 short sentence with zero padding, and the resource is front-loaded after the verb. The parenthetical detail about USD pricing is useful rather than wasteful.

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 no-parameter, no-output-schema listing tool, the description covers what is returned at a high level (agents, services, prices). It would be stronger if it hinted at the shape or volume of the results, but nothing essential for invoking it 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?

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline is 4. The description correctly does not invent any input requirements.

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 gives a specific verb ('Lista') and enumerates the resource contents: bank agents, their services, and prices in USD. An agent can tell this is a read-only catalog listing, though the term 'agentes del banco' is somewhat ambiguous about what kind of agents these are.

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?

There is no guidance on when to use this versus the sibling tools, nor any stated prerequisites or exclusions. The agent must infer that this is the discovery/entry-point tool for the catalog from the word 'Lista' alone.

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 burden, and it does disclose two genuinely important traits: the query costs $0.02 USD via x402 (a paid call the agent must budget for) and results are produced 'Sin IA' (deterministic retrieval, not generated). It does not explain the payment mechanics (wallet/signature flow), latency, or failure behavior, which matter for a paid endpoint.

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 name/domain is front-loaded, followed by the return payload and then two short operational flags (no AI, price). It is dense but every sentence carries information; the only friction is unexplained internal jargon such as 'alertas R1 a R6', which costs the reader without adding selectable 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?

There is no output schema, so the description must describe the return payload, and it does so explicitly (materia, autoridad, artículos con estado, plazos, alertas, normas/conceptos/sentencias). Combined with 100% schema coverage on inputs and the cost disclosure, an agent has enough to decide and call; only the opaque R1-R6 codes and payment flow remain underspecified.

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 enum for 'materia' is fully self-documenting, so the schema already does the heavy lifting and the baseline of 3 applies. The description hints at 'materia' as an input but adds no guidance on how 'contexto' vs 'pregunta' should be split, which is the one genuinely ambiguous choice.

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 names a specific resource (Consulta Mercantil: derecho comercial y jurisprudencia, Colombia) and enumerates what a consultation returns (materia, autoridad, artículos con estado, plazos, alertas R1-R6, normas/conceptos/sentencias cercanos). It is clearly a legal-research lookup, distinguishable in kind from the sibling verification/radar tools, though it never explicitly contrasts itself with any of them.

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 only implied: the enumeration of commercial-law outputs signals that this is the tool for Colombian commercial-law questions. There is no explicit when-to-use vs when-not, and no routing guidance relative to siblings such as empresa_mipyme__orientar or verificador_rues__verificar, which an agent might reasonably confuse for a company-law question.

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 burden. It does disclose two genuinely useful traits: the result is deterministic code-based rules (not AI) and each call costs $0.02 USD via x402, which signals a paid endpoint the agent should not call casually. It says nothing about whether the tool is read-only, what the response contains, or how failures/insufficient data are handled.

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?

It is short, but the first two sentences are redundant restatements of the same idea (Ruta Mipyme / ruta para crear una mipyme). The cost and no-AI facts earn their place; the duplication does not.

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 31-parameter, no-annotation, no-output-schema tool, the description is too thin: it never explains what the response looks like (route/steps/requirements), nor how to call it with a partial set of inputs. An agent can identify the topic but cannot predict the outcome of a call.

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 31 parameters are already documented field by field. The description adds no semantics beyond the schema – notably it never mentions the ciiu-vs-descripcion alternative or the minimal viable input set, which is the main thing an agent would need to know given all parameters are optional.

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 names a verb-like function ("guía/orientar") and a resource (creating a mipyme in Colombia), and adds that it is rule-based (R1–R8, no AI). But "orientar/guía" is vague about what the agent actually gets back – a step-by-step route, a diagnosis, a checklist of obligations – so it does not fully distinguish itself from siblings like 'registro_marca__ruta' or 'ruta_tac__revisar'.

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?

There is no statement of when to call this versus the other ruta/consultar tools, and no guidance about prerequisites or what a user must supply first. The reader must infer the use case entirely from the title-ish first sentence.

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 burden and does add real behavioral context: it discloses the per-call cost ($0.01 USD via x402) and the shape of what comes back (aggregates plus a capped set of 10 recent contracts). It stops short of describing failure modes, empty-result behavior, or what the 10-contract cap implies for older ranges.

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 short sentences, front-loaded with domain and scope, then result contents, then cost. No filler and no repetition of the tool name.

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?

There is no output schema, so the description must convey return values, and it does so adequately by naming the aggregate blocks and the 10 recent contracts. Cost is covered; only edge-case behavior (invalid or unknown NIT, date-range effects) is left 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 description coverage is 100%, so both 'nit' and 'desde' are already fully documented, including the default 2022-01-01 and the natural-person exclusion. The description adds nothing about parameter semantics, 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?

States the resource and domain precisely: contracting history for a supplier in SECOP II (Colombia), and enumerates what is returned (totals, main entities, modalities, 10 recent contracts). It does not explicitly name the sibling radar_secop__riesgo as the alternative for risk scoring, so differentiation is implied rather than stated.

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 frames the tool as a history/lookup radar, which implies when to use it, but gives no explicit when-not conditions or comparison to radar_secop__riesgo or verificador_rues__verificar. The natural-person exclusion only appears in the schema, not in the description.

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?

No annotations are supplied, so the description carries the full burden. It does disclose genuinely useful behavior: a $0.05 USD per-query charge via x402 payment and that results are deterministic ('Sin IA'), which an agent needs before calling. It omits error behavior, rate limits and the shape of the response, leaving meaningful gaps for a paid, unaudited tool.

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 telegraphic fragments, front-loaded with the resource, and each carries information (scope, data sources, no-AI, price). It is efficient, though the fragmentary style is slightly choppy rather than fully structured.

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 two-parameter lookup with no output schema, the description usefully enumerates the result categories and states the cost, which covers the essentials. It still does not describe the response structure, what 'señales explicadas' concretely yields, or how failures are surfaced.

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% with only two parameters, so the schema already explains the NIT constraint (companies only, not natural persons) and the desde date default. The description adds no syntax or format detail beyond that, which matches the 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?

The description names a specific resource (SECOP II contracting radar for Colombia) and enumerates what the result contains: contract history, SECOP I fines, RUES cross-reference and explained signals. It does not explicitly differentiate itself from the sibling radar_secop__proveedor, and the verb is implied rather than stated, so it falls short of a 5.

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?

There is no guidance on when to choose this over radar_secop__proveedor or verificador_rues, nor any statement of prerequisites beyond the mention that it 'no consulta personas naturales' (which lives in the schema). The cost note gives a weak decision signal but no usage routing.

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?

No annotations are supplied, so the description carries the full behavioral burden. It discloses two useful facts — no AI is involved ("Sin IA") and each query costs $0.02 USD via x402 — but says nothing about side effects, idempotency, latency, failure modes, or what the response actually looks like beyond a list of source types. For a paid consultation tool with zero annotation coverage this is a substantial gap, though the cost/payment disclosure keeps it from the bottom of the scale.

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?

It is short and front-loads the domain, and the cost sentence is efficiently stated. However, "Lo mismo, más..." is a wasted and actively confusing opening clause that depends on context the agent does not have, and "Experto en Marcas: registro de marca en Colombia" partly restates itself.

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 9-parameter, no-output-schema, no-annotation tool, the description does sketch the return contents (cited articles with text, norms, SIC concepts, Andean Tribunal interpretations, with links) and discloses cost and payment protocol. It still omits output format, how the answer is structured, and any guidance on how the many optional inputs (fechas, contexto, pregunta) shape the result.

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 all nine parameters, including why solicitante changes the fee and how productos drives Niza class suggestions. The description adds no parameter-level meaning of its own, so the baseline of 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?

The description opens with a role label ("Experto en Marcas") and a noun phrase ("registro de marca en Colombia") but never states a verb for what the tool actually does — answer a trademark question? register? assess? The second sentence says it returns cited articles, norms, SIC concepts and Andean Tribunal interpretations, which hints at a consultation/answer tool, but the dangling "Lo mismo, más..." refers to an unnamed sibling and leaves the boundary with registro_marca__ruta unresolved.

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?

"Lo mismo, más los artículos citados..." implies a relationship to another tool but never names it or states the condition for choosing one over the other. There is no when-to-use, when-not-to-use, or prerequisite guidance, so the agent must infer the routing decision from the parameter set alone.

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 at all, the description carries the full burden and does disclose two non-obvious traits: a hard cost ('$0.01 USD por consulta (x402)') and that the output is deterministic rule content, not model generation ('Sin biblioteca ni IA'). It also enumerates what the response contains (normas, tasas SIC, clases de Niza sugeridas, plazos, alertas R1–R8), though it says nothing about payment failure behavior or latency.

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 and scope are front-loaded in the first clause, followed by output contents and then the cost caveat. It is dense but every sentence carries information; 'Experto en Marcas:' is slight filler and 'Sin biblioteca ni IA' is terse enough to be ambiguous, but overall there is little 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?

For a 9-parameter, all-optional, no-output-schema tool, the description does the important work: it enumerates the deliverable artifacts (normas, tasas, clases sugeridas, plazos, alertas R1–R8) and flags the payment requirement. The remaining gap is sibling differentiation against registro_marca__consultar, which an agent must guess at.

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 with constraints and two enums. The description adds only loose echoes ('clases de Niza sugeridas', 'revisión del signo') and does not clarify how marca/pregunta/contexto interact or which combinations are required, 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?

States a specific verb and resource: 'registro de marca en Colombia' plus 'Trámite y autoridad, paso a paso', which frames it as a procedural roadmap rather than a lookup. It never names the sibling registro_marca__consultar, so the distinction is inferable ('paso a paso' vs. a plain query) but not explicit.

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 phrase 'paso a paso con sus normas, tasas oficiales... plazos y alertas' implies this is the tool for someone walking through the filing process, but there is no explicit when-to-use/when-not statement and no routing to registro_marca__consultar or verificador_sic__verificar. Usage is implied rather than instructed.

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 burden and does disclose meaningful traits: deterministic rules R1-R8 executed in code, 'sin IA', and a per-query cost of $0.02 USD via x402 (a payment rail the agent must handle). It does not say what the review returns, whether it is read-only, or what happens on payment failure, so the disclosure is partial.

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 the tool's identity before the mechanism and cost. No filler, though the cost note could be integrated more tightly with operational guidance.

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 7-parameter tool with nested objects and no output schema, the description conveys scope, mechanism, determinism, and pricing. The main gap is the return shape and how the returned 'revisión' should be interpreted, but the domain framing is largely sufficient.

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 every parameter is already documented in the schema, including the tramite enum and the proyecto-integral default. The description adds no additional semantics about how documento text or fechas are consumed, 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?

Names a specific role and resource: revisor tributario, aduanero y cambiario for Colombia, plus the mechanism (ruta de pasos, rules R1-R8, library articles). Clear enough to distinguish from a generic search tool, but it never contrasts itself with siblings like derecho_comercial__consultar or empresa_mipyme__orientar.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no routing to alternatives among the nine sibling tools. The agent must infer that this is for tax/customs/currency review based on the domain wording alone.

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?

No annotations are provided, so the description carries the full burden. It does disclose two useful traits: rule-based with no AI ('Sin IA'), and a $0.02 USD per-query cost via x402 payment. That cost/settlement disclosure is genuinely decision-relevant, but it says nothing about what happens on an invalid or unfound NIT, error behavior, or result shape.

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 short sentences, front-loaded with the registry and jurisdiction before the behavioral cost note. No filler. Minor deduction for the unexplained 'x402' abbreviation, which some agents may not resolve.

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 one-parameter lookup this is close to adequate: purpose, jurisdiction, cost and determinism are all covered. However, with no output schema the description should hint at what the response contains (exists / status / renewal date), and it should note the failure mode for an unmatched NIT.

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 'nit' parameter is already documented in the schema, including that dots, hyphens and the check digit are accepted. The description's 'por NIT' adds no syntax or format detail beyond that, so the baseline of 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: it verifies (existence, status, matrícula renewal) a Colombian RUES company by NIT. That specificity (jurisdiction, registry, the three things checked) distinguishes it from siblings like verificador_sic__verificar and registro_marca__consultar without the agent needing to open 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?

There is no explicit when-to-use or when-not-to-use guidance and no naming of alternatives. The agent must infer from the parenthetical '(Colombia)' and the RUES label that this is the registry-of-companies check rather than the SIC or trademark tools. Nothing tells the agent what to do if it needs broader company data instead.

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 burden. It usefully discloses cost ($0.01 USD via x402), latency (milliseconds), and that verification runs deterministic code rules R1–R8, but it does not describe the response shape, error behavior, or what a failed verification looks like.

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 with zero wasted wording: purpose first, then method, speed, and price. The information is front-loaded and each sentence contributes a distinct fact.

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 paid verification tool with no output schema and no annotations, the description covers payment, speed, and rule-based method but omits what the verification returns and what R1–R8 actually check. It is adequate to start a call but incomplete for interpreting results.

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 in the input schema. The description adds no parameter-level meaning beyond what the schema provides, making the baseline score of 3 appropriate.

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 resource and action: a verifier for paid publications in Colombia, using rules R1–R8. It is clearly distinct from registry or legal-consultation siblings in domain, though it never explicitly names an alternative tool to avoid confusion with verificador_rues__verificar.

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 implies the tool is for checking paid social-media publications, but gives no explicit when-to-use, when-not-to-use, or alternative-tool guidance. An agent must infer the appropriate context entirely from the description's domain wording.

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