MCP Puerto Rico Sentencias

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

No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose that the content is public and secondary, which usefully signals that this is a read-oriented research search. However, it does not mention result limits, pagination, recency, or whether full articles are returned, leaving some behavior unspecified.

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 a single, front-loaded sentence with no filler or redundant details. Every word adds relevant information about the tool's source, scope, and nature.

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?

The tool is relatively simple, has an output schema, and only two parameters, so the description does not need to explain return values. However, the lack of any parameter-level documentation and limited behavioral detail leaves some important operational aspects, especially the meaning of 'maximo', 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 0%, so the description must compensate for the missing parameter explanations. It does not describe 'consulta' or 'maximo' at all, aside from implying a search action. An agent must infer that 'maximo' limits the number of results, which is not stated anywhere in the tool definition.

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 ('Busca'), a concrete resource ('contenido público de Microjuris Al Día'), and a clear purpose ('como fuente secundaria de actualidad'). This distinguishes it from the sibling jurisprudence-focused tools, making it clear this is a current-news secondary-source search 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?

The description gives clear context: use this tool to search public content from Microjuris Al Día as a secondary source of current legal developments. It implies a distinction from primary-source research tools, though it does not explicitly name alternatives or state when not to use it.

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 of behavioral disclosure. It only describes the search function and the 'visible links' scope, adding nothing about read-only safety, rate limits, pagination, access restrictions, or output behavior. The behavioral information is barely more than the function statement itself.

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?

A single front-loaded sentence with no filler. The verb and target resource appear immediately, and every word earns its place. The size is appropriate for a low-complexity tool.

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?

Although the tool is simple (2 params, 1 required, output schema present), the lack of annotations and 0% schema coverage place a heavy burden on the description. With numerous sibling tools and no differentiation or behavioral guidance, an agent cannot reliably determine when or how to invoke this tool 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%, yet the description explains neither 'consulta' nor 'maximo'. The parameter names are self-evident in Spanish (query and maximum), which prevents a score of 1, but the description adds no clarification about query format or what maximo limits (result count, links, etc.).

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 ('Busca') and a specific resource ('enlaces visibles en la Biblioteca Jurídica Virtual del Departamento de Estado'), which distinguishes it from siblings like buscar_sentencias and buscar_actualidad_juridica. The phrasing 'enlaces visibles' is slightly ambiguous about whether it returns links or searches link content, but the scope is clear.

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 tool versus the many siblings such as buscar_sentencias, investigar_sentencias, or buscar_por_cita. With a large and partly garbled sibling set, the agent is left to infer the appropriate use case without any explicit conditions or exclusions.

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 behavioral disclosure burden. It usefully discloses a non-obvious trait: no external request is made, meaning the tool operates offline against local data. However, it does not describe output format, result behavior, whether maximo actually caps results, or any error conditions.

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 a single sentence with the core action and scope front-loaded, followed by a useful behavioral constraint. There is no filler or redundant restating 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?

For a simple two-parameter local search, the core purpose is clear, but the description does not clarify what 'candidatos TSPR' means, what a candidate result looks like, or how 'maximo' behaves. With no output schema and no annotations, these gaps remain for the agent to guess.

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%, and the prose does not explain either parameter. 'consulta' and 'maximo' are reasonably self-explanatory names, but the meaning of 'maximo' as a result limit and how it interacts with the search is left entirely to inference. The description fails to compensate for the lack of schema-level parameter documentation.

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 ('Busca'), a specific resource ('candidatos TSPR'), and a clear scope ('solo en el corpus local'). It also distinguishes this tool from siblings by explicitly noting that it makes no external request, so an agent can separate it from broader or external search tools.

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 gives clear usage context: this tool is for searching only the local jurisprudence corpus and deliberately avoids external calls. It does not explicitly name alternatives or provide when-not-to-use conditions, but the local-only and no-external-request constraints are enough to guide tool 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?

With no annotations provided, the description carries the full burden. 'Busca' implies a non-destructive read operation and 'públicas' suggests accessible public records, which is useful context. However, it does not disclose pagination, ordering, result limits, or source coverage 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 description is a single, front-loaded sentence with no filler. Every word adds precision by specifying the court, the finality, the publicity, and the type of legal determination being searched.

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?

The output schema covers return shape and the core purpose is stated, making the tool minimally usable. However, with many sibling search tools and no usage guidance, an agent lacks sufficient context to reliably select this tool over alternatives.

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%, and the description says nothing about consulta, ano, or maximo. The Spanish property names and defaults are self-evident, but the description itself adds no parameter-level meaning to compensate for the lack of 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 uses a specific verb, 'Busca,' and identifies a clear resource: 'determinaciones finales públicas del Tribunal de Apelaciones.' This clearly distinguishes it from generic sentencia searches by court and document type, though it does not explicitly name sibling alternatives.

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 gives no guidance on when to use this tool instead of siblings such as buscar_sentencias or investigar_sentencias. The intended use is only implied by the resource phrase, with no exclusions or alternative 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?

There are no annotations, so the description carries the burden of disclosing behavior. It does reveal the key behavior: searching for decisions and verifying relevance in official PDFs, implying document retrieval and inspection. However, it does not disclose output shape, result-handling details, or any side effects of fetching PDFs.

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 a single, front-loaded sentence with no filler. Every word contributes to explaining what the tool does and how it behaves.

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?

Although an output schema exists, the 0% parameter coverage and the absence of sibling-selection guidance leave an agent uncertain about the meaning of maximo/paginas and about when to choose this tool among many legal-research alternatives. The definition is clear on core purpose but incomplete for confident invocation in a crowded toolset.

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%, and the description adds no information about the parameters. 'maximo' and 'paginas' are ambiguous (maximum results? maximum pages per PDF?), and 'consulta' is not explained. The description must compensate for the bare schema but does not.

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 action, 'Busca', and a clear resource: decisions/orders of the JRT. It adds the distinctive behavior of verifying relevance in official PDFs, which helps differentiate it from broader sibling tools like buscar_sentencias. It does not explicitly name an alternative, so it stops just short of a top score.

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 tool versus the many related siblings such as buscar_sentencias, buscar_decisiones_apelaciones, or investir_sentencias. The only implied context is JRT-related decisions with PDF verification, but no exclusions or alternative-selection criteria are provided.

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?

There are no annotations, so the description carries the behavioral disclosure burden. It discloses that results are not verified and are not a substitute for legal research, which is useful. However, it does not state other behavioral traits such as whether it only reads data, what the output represents, or how the auxiliary directory may differ from the main legal corpus.

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 filler. The primary action is front-loaded, and the second sentence adds a meaningful limitation rather than repeating the tool name or purpose.

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?

The tool is simple, and an output schema exists, so return-value documentation is not necessary. Still, the description leaves gaps: no parameter semantics, no explicit relationship to the many sibling research tools, and no clarification of what 'casos semilla' means behaviorally.

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 compensate for the undocumented parameters. The description does not mention 'consulta' or 'maximo' or explain how they influence the search. Only the standalone word 'Busca' makes 'consulta' partially inferable, but 'maximo' receives no semantic 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?

The description clearly identifies a specific action and resource: searching 'casos semilla del directorio auxiliar,' so it is not a tautology. The added clause 'No verifica ni sustituye la búsqueda jurídica' helps distinguish it from verification-oriented research tools, though it does not explicitly name sibling alternatives.

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 implies the tool is for finding seed cases in the auxiliary directory, which gives some context. It also includes a when-not signal ('No verifica ni sustituye la búsqueda jurídica'), but it does not name a preferred alternative tool or specify conditions under which this should be selected over 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?

No annotations are present, so the description carries the behavioral disclosure burden. It conveys a multi-source aggregation behavior and strict verification filtering, but does not explain what the verification levels are, how results are prioritized, or the exact nature of the returned authorities.

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 compact sentence with no filler, and the core idea is front-loaded. It could carry more useful detail without becoming verbose, but as written it is efficient.

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 tool with four parameters, no annotations, many overlapping siblings, and no schema descriptions, this single sentence is insufficient for reliable selection and invocation. The description omits selection criteria, parameter effects, and behavioral details needed to distinguish it from alternatives.

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 0% schema description coverage, the description needed to clarify argumento, maximo, ano_apelaciones, and incluir_actualidad. It only generally maps 'cuestión jurídica' to the query and adds almost no parameter-level meaning, though the parameter names and defaults are somewhat self-explanatory.

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 clear activity: investigating a legal question across several sources with strict verification. The resource ('cuestión jurídica') and method ('varias fuentes', 'niveles estrictos de verificación') are identifiable, but it does not distinguish from sibling research tools such as buscar_sentencias or investigar_derecho_pr.

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?

No explicit when-to-use or when-not-to-use guidance, and no named alternatives. The strict-verification phrasing implies it is appropriate when multi-source, high-confidence legal research is needed, but it leaves exclusion conditions unstated.

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 burden and does so richly: it discloses the internal loop, global candidate pool, verification against official PDFs, relevance reordering, iterative Top-K stabilization, conservative budget, and possible fewer results. This gives an agent accurate expectations not inferable from the schema.

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, the usage trigger is clearly separated in caps, and the remaining sentences provide necessary behavioral detail without fluff. Every sentence contributes to selection or invocation understanding.

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 search/ranking tool, the description covers purpose, algorithm, caveats, and output limitations, and an output schema is available for return details. The main remaining gap is the lack of explicit semantics for maximo and the date-range parameters, which prevents it from being fully self-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 0%, and while the phrase 'argumento' and 'Top N' loosely map to the argumento and maximo parameters, the date-range parameters ano_desde and ano_hasta receive no semantic explanation. The description does not make up for the lack of schema descriptions, especially for optional parameters.

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 specific verb and resource: 'Busca las mejores decisiones TSPR para un argumento'. It also distinguishes itself from siblings by stating it does not search year-by-year and does not favor recent cases, so an agent can recognize its specialized ranking purpose.

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 gives explicit trigger conditions: 'USA ESTA HERRAMIENTA cuando el usuario pida "las mejores", "más relevantes" o "Top N"'. It also notes what the tool does not do, but it does not name an alternative sibling for general-case searches, so the routing guidance stops just short of fully complete.

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. It discloses an important behavioral guardrail: nonexistent citations will not be substituted or replaced. This meaningfully prevents the agent from expecting fuzzy matches or fabricated results.

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 a single sentence with no filler, and the key action ('Localiza una cita TSPR exacta') is front-loaded. Every word 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?

For a single-parameter lookup tool with an output schema, the description covers the core purpose and a key behavior. However, it omits citation format details and does not explicitly position the tool among the many sibling search tools, so the overall context is only minimally complete.

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 clarify the parameter. It adds that 'cita' should be an exact TSPR citation, which is useful, but it does not provide a format, example, or explanation of what counts as an exact citation, leaving a 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 uses a specific verb ('Localiza') and a specific resource ('una cita TSPR exacta'), making the core action immediately clear. The phrase 'sin sustituir citas inexistentes' also distinguishes it from fuzzy or fallback search tools among the siblings.

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 exact-match language implies this tool should be used when the agent has a precise TSPR citation to look up. However, it does not explicitly state when-not-to-use it or name an alternative sibling, leaving some selection inference to the agent.

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 provided, the description carries the full burden of behavioral disclosure, but it only states the basic search action. It does not mention read-only behavior, result limits, pagination, potential errors, or any side effects.

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 a single sentence with no fluff and is easy to read. However, it is under-specified rather than efficiently concise, lacking any operational detail that would help an agent.

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 tool with three parameters, no annotations, and sibling tools with overlapping functionality, the description is too thin. It does not explain how to construct a query, what the output contains, or when this tool is preferred over similar ones.

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%, and the description provides no information about how 'consulta', 'ano', or 'maximo' should be used or how they affect the search. The parameter names are somewhat self-explanatory, but the description adds no meaning beyond the bare 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 clearly states the tool searches for judgments and opinions of the Supreme Court of Puerto Rico, with a specific verb ('Busca') and a specific resource. However, it does not explicitly differentiate itself from closely related siblings like investigar_sentencias or buscar_mejores_sentencias.

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?

No guidance is provided about when to use this tool versus alternatives such as investigar_sentencias, buscar_mejores_sentencias, or leer_sentencia. There are no exclusions, prerequisites, or selection criteria stated.

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 behavioral disclosure burden. The verb 'Lista' implies a read-only catalog operation, and the description clarifies what is returned (collections and source hierarchy), but it does not mention side effects, freshness, availability, or any operational constraints.

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 a single clear sentence with no filler, repetition, or unnecessary detail. The core action and object are front-loaded, making it easy for an agent to parse quickly.

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 that the tool has no parameters and an output schema exists, the description is mostly complete for a simple catalog-listing tool. The main omission is explicit guidance on when to choose this over sibling catalog-like tools, but the zero-parameter nature and clear purpose keep the tool low-complexity.

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 has zero parameters, so the baseline is 4; there are no parameter semantics to explain. The description appropriately focuses on the fixed behavior of the tool rather than parameters.

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 uses a specific verb ('Lista') and a specific resource ('colecciones públicas integradas y su jerarquía de fuente'), making the tool's function immediately clear. It also stands apart from sibling search and state tools by describing a catalog/listing action rather than a search or mutation.

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?

No guidance is provided about when to use this tool instead of related siblings such as 'buscar_biblioteca_juridica' or 'estado_directorio_autoridades'. The usage context is only weakly implied by the word 'catálogo' and the zero-parameter design.

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 provided, the description carries the transparency burden and does so well: it discloses automatic searching, per-candidate verification before acceptance, and the important interpretive rule that absence of repeal is not automatically vigencia. It does not mention side effects or auth requirements, but the described behavior is materially transparent for an agent.

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 compact sentences lead with the main action, then explain the source and workflow, and end with a critical caveat. Every sentence earns its place and the most decision-relevant limitation is stated plainly.

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?

The description covers purpose, source, workflow, and an interpretive limitation, while the output schema accounts for return structure. The main gap is the absence of explicit routing among the vigencia-related sibling tools, but the information provided is sufficient for correct selection and 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 0%, so the description must compensate. It ties 'ley' and 'articulo' to the objects being searched and notes that no seed URL is needed, which adds meaning beyond the schema. However, it gives no format, syntax examples, or explanation of how the article parameter combines with the law parameter.

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 specific action: automatically searching SUTRA for later laws that affect a law or article. It also clarifies that the tool is about discovering legislative-history relationships, not delivering a final validity verdict, which distinguishes it from the verificar_vigencia siblings.

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 states the source (official public SUTRA portal), the workflow (opening each detail before accepting a relationship), and that no user seed URL is needed. The caveat that absence of a detected repeal is not automatically vigencia effectively excludes this tool for final validity checks, though it does not explicitly name the alternative sibling.

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 of behavioral disclosure, but it only mentions 'compatibility' and 'historical diagnosis' without explaining what happens when called, whether it reads or mutates, or what the response represents. This is insufficient for an agent to anticipate tool 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 description is short as a single sentence, but it does not earn its place because the content is vague and uninformative. It is under-specified rather than efficiently concise.

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?

Although there are no parameters and an output schema exists, the description is too vague to be contextually complete. The agent remains unclear about the tool's purpose and when to choose it over the many sibling status 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 input schema has zero parameters, so there is no parameter documentation burden. A baseline score of 4 applies because the description does not need to compensate for undocumented parameters when none exist.

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 'Compatibilidad con el diagnóstico histórico del núcleo de sentencias' lacks a clear verb and resource. It suggests a compatibility/status concept related to historical diagnosis of sentence cores but does not state what the tool actually does, making it hard to distinguish from sibling status tools like estado_corpus_jurisprudencia.

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 tool versus alternatives. The description offers no context, exclusions, or references to sibling tools, leaving the agent to guess the appropriate invocation scenario among many similar-looking status tools.

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. It discloses a useful trait: no network access is performed, and 'local persistente' indicates the data source. However, it does not explicitly state that the tool is read-only or describe what 'estado real' includes or how the result is returned.

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 a single, front-loaded sentence with no filler. Every part contributes: the action, the resource, the local persistence, and the no-network behavior.

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 zero-parameter status tool, the description is largely complete: it identifies what is reported and the key limitation. It could be improved by explicitly confirming no side effects and by naming what aspects of the corpus state are covered, but no critical calling information 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 input schema has zero parameters, so the description need not explain parameter meaning. The 0-parameter baseline of 4 applies, and the description's purpose statement is sufficient.

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 clearly states a specific action and resource: 'Reporta el estado real del corpus local persistente'. It is distinct from sibling state tools like estado_directorio_autoridades by naming the persisted legal corpus, though it does not explicitly name a sibling alternative.

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 'sin hacer acceso de red' implies this tool is appropriate when the agent needs local, offline corpus status. However, it gives no explicit when-to-use vs alternatives, such as 'use this instead of buscar_corpus_jurisprudencia for local-only checks'.

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?

Tool has no description.

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?

Tool has no description.

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?

Tool has no description.

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?

Tool has no description.

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?

Tool has no description.

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?

Tool has no 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?

There are no annotations, so the description carries the burden of behavioral disclosure. 'Diagnóstico' implies a read-only status inspection, and 'corpus local persistente' adds some context about what is being examined, but the description does not explicitly confirm that the tool has no side effects, does not mutate data, or has any relevant access or freshness characteristics.

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 a single concise sentence that front-loads the core purpose and then adds the important scope detail about the persistent local corpus. Every word contributes meaning, and there is no redundancy or fluff.

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 zero-parameter diagnostic tool with an output schema, the description is mostly sufficient: it states the purpose and scope without needing to explain return values. It is slightly incomplete because it does not clarify how this status report relates to the overlapping estado and estado_corpus_jurisprudencia tools, but invocation risk is low due to the empty schema.

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 input schema has zero properties, so there are no parameter semantics to clarify. The description adds contextual meaning by identifying what the diagnostic covers, and the baseline for zero-parameter tools is 4.

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 clearly states that the tool provides a diagnosis/status of legal research and explicitly includes the persistent local corpus. It is not a tautology and gives a reasonable sense of the tool's resource and scope, though it lacks an explicit action verb and does not differentiate itself from similar estado_* sibling tools.

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?

No guidance is provided about when to use this tool versus sibling tools such as estado, estado_corpus_jurisprudencia, or estado_directorio_autoridades. There are no exclusions, alternatives, or contextual triggers mentioned, so an agent must infer usage solely from the name and one-line 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?

With no annotations, the description carries the full burden and does it well: it discloses that the tool is conservative, multi-source, non-synthesizing, and returns candidates separated by source and hierarchy. It omits operational details such as error behavior or data freshness, but the core behavior is clearly communicated.

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 three sentences with no wasted words: scope first, then coordinated sources, then the key non-synthesis constraint. The structure is clear and front-loaded, though it could have integrated parameter guidance without becoming bloated.

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?

The output schema covers return shape, and the description gives enough behavioral context for a non-destructive research tool. However, with three parameters and zero parameter documentation in either the schema or the description, the agent is left to guess how to construct a valid consulta and when to set ano or maximo.

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%, and the description never explains consulta, ano, or maximo. The parameter names suggest their meaning, but the description adds no semantic guidance beyond the schema, leaving the agent to infer how to formulate the query or use the optional filters.

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 is specific: it coordinates Supreme Court case law, Court of Appeals public decisions, and official catalogs, and delivers candidates separated by source and hierarchy. It also distinguishes itself from synthesis tools by explicitly stating it does not fuse or invent a legal conclusion.

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 states the intended use: when the MCP client needs traceable, source-separated candidates to analyze itself. It also gives a clear behavioral exclusion ('No fusiona ni inventa una conclusión jurídica'), although it does not name specific sibling alternatives.

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 of disclosing behavioral expectations. 'Verificables' and 'por contenido del documento' hint at filtering behavior, but the description does not explain data sources, access requirements, limitations, or what verification means in practice.

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 a single front-loaded sentence with no filler, which is concise. However, it omits usage and parameter context, so the brevity comes at the cost of completeness.

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 search tool with 3 parameters, no annotations, 0% schema description coverage, and a large sibling list, this description is not complete enough. It leaves the agent with insufficient information to confidently select this tool or construct well-formed arguments for anos and maximo.

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 compensate, but it does not explain consulta, anos, or maximo beyond their names and defaults. The phrase 'por contenido del documento' loosely maps to consulta, but no query syntax, input format, or effect of the year range or maximum is described.

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 uses a specific verb ('Encuentra') and a concrete resource ('autoridades TSPR verificables') with a clear search criterion ('por contenido del documento'), so an agent can infer it searches for verifiable Puerto Rico Supreme Court authorities based on document text. It is not a tautology, but it does not explicitly name or distinguish sibling tools such as buscar_sentencias or buscar_por_cita.

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 provides no explicit when-to-use guidance, exclusions, or alternatives. It only implies a content-based search, leaving the agent to choose among 23 sibling tools without clear direction on when this tool is preferred.

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 burden of behavioral disclosure. It signals a non-destructive read action ('Lee') and discloses important limitations, such as rejecting secondary sources and not assessing validity or subsequent treatment. It does not mention failure modes, authentication, or rate limits, but the core behavior is reasonably transparent for a read-only 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?

The description is three sentences with no redundancy: it states the core action and output, gives the intended use case, and lists limitations. Each sentence earns its place and the most important information is front-loaded.

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?

The description adequately covers purpose, use case, and limitations, and an output schema exists for return-value details. However, the complete absence of parameter guidance for 'consulta' and 'max_pasajes', combined with zero schema descriptions, leaves a notable gap in the knowledge needed to use the tool fully.

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%, and the description does not compensate. 'url' is only indirectly inferable as the authority to read, while 'consulta' and 'max_pasajes' are entirely unexplained, leaving the agent without guidance on how to use the optional parameters.

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 specific verb ('Lee'), a precise resource type ('autoridad primaria pública'), and a concrete outcome ('devuelve pasajes textuales verificables'). It also distinguishes itself from related tools by explicitly stating that it rejects secondary sources and does not determine vigencia or tratamiento posterior.

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 explicitly states when to use the tool: to verify documents discovered by legal-research tools before citing them as support. It also gives clear negative guidance ('Rechaza fuentes secundarias', 'no determina vigencia ni tratamiento posterior'), but it does not name a specific alternative tool for those excluded cases.

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 provided, the description carries the disclosure burden. It states that the tool reads a public source and returns extracted passages, implying a read-only behavior, but it does not describe error behavior, output structure nuances, or limitations such as whether only publicly accessible URLs work.

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 one short, focused sentence with no filler. It front-loads the action and object and effectively communicates the primary purpose in minimal space.

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?

While an output schema exists and the tool appears simple, the description omits how to use the optional parameters and gives no guidance for selecting this tool over its many siblings. An agent needs more context to invoke this tool correctly with the right parameter semantics.

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 compensate for the parameters, but it does not. It mentions 'fuente' and 'pasajes', which vaguely relates to url and max_parrafos, but it never explains how 'terminos' filters results or how 'max_parrafos' controls output volume.

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 uses the specific verb 'Lee' and identifies the resource ('sentencia pública') and the outcome ('devuelve pasajes extraídos de la fuente'). It is clear about the tool's core function, though it does not explicitly differentiate from siblings like buscar_sentencias.

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 implies a clear use case: read a public judgment from a provided URL and obtain extracted passages. However, it gives no explicit conditions for when to choose this tool over siblings such as buscar_sentencias or investigar_sentencias, nor does it state any exclusions.

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?

The verb 'Explica' indicates an informational, non-mutating behavior, which is useful given that no annotations are provided. However, the description does not disclose what the returned content looks like, whether it is static help text, or how the 'campo' and 'consulta' parameters affect the response.

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 a single sentence with no filler and fronts the core purpose. However, it is so terse that it omits necessary context about parameters and usage, so it is not fully appropriately sized.

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 lack of annotations, zero parameter descriptions, and a large set of search-related siblings, the one-sentence description is insufficient for an agent to confidently determine when to call the tool or what inputs to provide. The output schema reduces the need to describe return values, but does not compensate for the missing usage and parameter guidance.

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 schema has 0% description coverage, and the description never mentions 'campo' or 'consulta'. It therefore adds no meaning beyond the parameter titles and defaults, leaving the purpose of 'consulta' especially unclear.

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 uses a concrete verb ('Explica') and identifies a resource (the sources and filters of the jurisprudential core), so it is reasonably clear that this is an explanatory/help tool rather than another search sibling. However, 'núcleo jurisprudencial' is left undefined, and several sibling tools are also source-related, so it does not fully distinguish itself.

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?

No explicit guidance is given about when to call this tool versus alternatives such as buscar_sentencias, catalogo_fuentes_juridicas, or politica_vigencia_fuentes. The only implication is that it provides background on search options, but there are no stated conditions, exclusions, or recommended contexts.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It indicates the tool is explanatory, but it does not state that the tool is purely informational, does not perform searches, does not mutate state, or what kind of response to expect. More behavioral context is needed.

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?

A single, focused sentence that directly states what the tool explains. There is no redundancy or filler, and the key topic is front-loaded.

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 zero-parameter explanatory tool with an output schema, the description is largely sufficient: it names both content areas covered. It could be more complete with a note about when to use it or what kind of answer it provides, but the low complexity and presence of an output schema reduce the burden.

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 has zero parameters, so the baseline is 4. The description does not need to explain parameter semantics because there are none to document.

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 clearly states the tool's purpose: explaining the hierarchy used for validity and the role of SUTRA/CodeXPR. It uses a specific verb ('Explica') and names a concrete resource/topic, which makes it distinguishable from the search- and verification-focused sibling tools, though it does not explicitly differentiate itself by name.

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: an agent can infer this tool should be invoked when an explanation of the validity hierarchy or SUTRA/CodeXPR's role is needed. However, the description gives no explicit guidance on when to use it versus alternatives like verificar_vigencia_ley or verificar_vigencia_legislativa.

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 provided, the description carries the behavioral burden. It discloses that the tool does not guess validity and specifies the fallback behavior when official evidence is inconclusive, returning estado_vigencia = no_determinada and puede_afirmarse_vigente = false. It could add more detail about handling invalid URLs or successful resolution, but the essential behavior is clear.

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 purpose and every subsequent sentence adds necessary guardrail information: when to use it, allowed sources, why secondary indexes are insufficient, and fallback behavior. No sentence is wasted.

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 high-stakes legal context and the presence of an output schema, the description covers the critical operational context: when to invoke, what URLs are acceptable, what not to rely on, and what to return when evidence is inconclusive. This is sufficient for an agent to use the tool 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 compensate for the bare parameter names. It explains that url_oficial must be an official source and references laws, codes, and articles, giving some context. However, it does not define expected formats for ley or articulo, such as whether ley is a number, name, or citation.

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 specific verb and resource: it verifies signs of amendment/repeal on an official URL, and explicitly states it does not guess validity. This clearly distinguishes the tool from simple validity lookups and from sibling legal research tools.

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 gives explicit when-to-use guidance: before presenting a law, code, or article as vigente/actual/no derogado. It also gives clear restrictions on acceptable URL sources and warns that secondary indexes are insufficient, though it does not name a specific alternative sibling 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?

With no annotations provided, the description carries the full behavioral burden and succeeds remarkably well. It discloses the conservative decision logic, the handling of explicit derogation and amendments, the 'no_determinada' fallback when evidence is insufficient, and the critical rule never to affirm positive validity based only on absence of results.

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 uses four compact, information-dense sentences. The main action and conservative principle are front-loaded, followed by specific decision branches and the critical caveat. Every sentence earns its place and there is no redundant or filler 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?

The behavioral contract is clear, and an output schema exists to cover return values, so the core mission is understandable. However, with no annotations and zero schema description coverage, the underspecified inputs ('ley' and 'articulo') and the lack of sibling differentiation leave the description incomplete for reliably selecting and invoking this tool among similar legal-status 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?

Schema description coverage is 0%, and the description never mentions 'ley' or 'articulo'. The parameter names suggest some meaning: 'ley' is a law identifier and 'articulo' is an optional article, but the description does not explain expected formats, whether 'articulo' narrows the check, or how the law should be identified. The description adds no parameter semantics 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 ('verificar') and resource ('vigencia de ley') and clearly explains what the tool does: it runs SUTRA history, reports explicit derogation, enumerates amendments, and returns a conservative status. It is not a tautology and conveys a clear purpose, though it does not explicitly distinguish itself from the near-named sibling 'verificar_vigencia_legislativa'.

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 implies a use case: verify the current legal validity of a law, optionally scoped to an article. However, it gives no explicit guidance about when to use this tool instead of alternatives like 'verificar_vigencia_legislativa' or 'construir_historial_legislativo', and it does not state any exclusions or prerequisites.

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