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 only states that the tool 'busca' (searches) and mentions 'top_k' implies returning fragments. It does not disclose whether the operation is read-only, any authentication requirements, rate limits, or side effects. For a search tool, the read-only nature is intuitive, but the description does not explicitly confirm it, and no other behavioral traits are mentioned.

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 concise, with the purpose front-loaded and the parameter explanations kept brief. There is no filler or redundancy. The structure is clear and easy to parse, though it could be slightly more structured by separating the purpose from parameter details, but it is efficient overall.

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 search tool with an output schema, the description is fairly complete. It explains the parameters and implies the return of fragments. However, it lacks explicit usage guidance and behavioral transparency (e.g., confirming it is a read operation). These gaps prevent it from being fully comprehensive, though the output schema mitigates the need to describe the return format.

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 schema description coverage at 0%, the description compensates well by explaining both parameters: 'query' as a natural language query and 'top_k' as the number of most relevant fragments to return after reranking, with a default of 8. This adds meaning beyond the schema's minimal type definitions, giving the agent the necessary context for correct invocation.

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 in basic science books and lists the specific subjects (biochemistry, histology, anatomy, cell biology), which distinguishes it from sibling tools that cover other domains. It uses a specific verb ('Busca') and a concrete resource, making the purpose clear, though it does not explicitly name an alternative tool as some descriptions do.

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 usage context is implied by the subject list – if the query is about basic sciences, use this tool. However, there is no explicit guidance on when not to use it or how it compares to the sibling search tools (e.g., for physiology or pathology). The description relies on the user to infer the appropriate choice from the listed subjects.

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 does reveal a genuine behavioral trait - the reranking step ('tras el reranking') and that it returns the most relevant fragments - which adds value beyond the schema. However, it doesn't disclose other operational details such as rate limits, auth requirements, or error/empty-result behavior. Moderate disclosure for an unannotated search 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 compact and efficient - two lead sentences establishing purpose and use cases, followed by a clean Args list. Purpose and usage are front-loaded. There is no wasted wording, and it is appropriately sized for a two-parameter search 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?

The tool has an output schema (covering return values), both parameters are documented, and purpose and use cases are explicit. For a low-complexity search tool with two parameters, this is fairly complete. Minor gaps exist around error handling and result truncation, but these are not critical given the output schema and simple parameter set.

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%, but the Args section fully documents both parameters with meaningful semantics: query is described as a natural language query about pharmacology, and top_k as the number of most relevant fragments to return with its default of 8. This adequately compensates for the schema gap, though the descriptions are fairly basic and don't specify value ranges or formats beyond the default.

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 action ('Busca') against a specific resource (pharmacology books, naming Katzung, Goodman, Mendoza). It is clearly distinguished from sibling tools which target different subjects (fisiologia, patologia, propedeutica, basicas) - the domain separation is obvious from the title and description. The verb and resource are precise and unambiguous.

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?

'Úsalo para mecanismos de acción farmacológica, dosis, interacciones y efectos adversos' explicitly lists the use cases (mechanisms of action, doses, interactions, adverse effects). It provides clear context on when to invoke this tool, and the differentiation from siblings is implicit via subject domain. However, it doesn't explicitly state when NOT to use it or name an alternative tool by name.

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 hay anotaciones, por lo que la descripción debe asumir la carga. Menciona el paso de reranking y el valor por defecto de top_k, lo que da cierta transparencia sobre el proceso. No declara explícitamente que sea una operación de solo lectura, aunque el verbo 'buscar' lo sugiere. Falta información sobre límites o formato de respuesta.

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?

El texto es breve y directo, con la finalidad al inicio y la lista de parámetros al final. No hay redundancia ni información innecesaria; cada oración aporta contenido relevante.

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?

Para una herramienta de búsqueda con solo dos parámetros y un esquema de salida presente, la descripción cubre todos los aspectos necesarios: propósito, contexto de uso, y semántica de parámetros. No se echa en falta información sobre el formato de retorno porque el esquema de salida lo cubre.

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?

La cobertura del esquema es 0%, por lo que la descripción compensa completamente. Explica 'query' como consulta en lenguaje natural sobre fisiología, y 'top_k' como número de fragmentos tras el reranking con su default. Añade valor más allá del esquema, incluyendo contexto de uso.

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?

La descripción indica claramente el recurso ('libros de fisiología médica') y el propósito ('entender función normal, mecanismos fisiológicos, homeostasis y regulación'). Se distingue de los hermanos al especificar el dominio fisiológico, lo que permite seleccionarlo correctamente entre las otras búsquedas.

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?

La frase 'Úsalo para entender función normal...' establece un contexto de uso claro. Sin embargo, no menciona explícitamente cuándo no usarlo ni nombra las alternativas (buscar_patologia, etc.), por lo que la orientación es implícita más que directa.

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 states that the tool searches pathology books and returns relevant fragments after reranking, which discloses key behavior. It does not mention side effects, but for a read-only search tool this is not a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is succinct, front-loaded with the core purpose, then organized into an Args section. Every sentence adds value and there is no redundant or filler text.

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 retrieval tool, the description covers the domain, use case, parameters, and output behavior. An output schema exists for the return value, so that does not need to be explained. It could be strengthened by explicitly saying when not to use it or naming sibling tools, but it is otherwise 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?

The schema provides no property descriptions, but the 'Args' section fully compensates: 'query' is described as a natural-language pathology question, and 'top_k' is explained as the number of relevant fragments to return after reranking, including its default. This adds substantial meaning beyond the raw 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 a specific verb ('Busca') and a resource (pathology books: Robbins, Kumar, Rubin), and clarifies that it is for understanding disease mechanisms, morphological changes, and pathophysiology. It does not explicitly differentiate itself from the sibling tools, but the domain-specific scope makes the distinction clear enough.

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 says when to use the tool: to understand disease mechanisms, morphological changes, and pathophysiology. It does not provide exclusions or mention sibling alternatives, but the usage context is clear and actionable.

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. It conveys that this is a retrieval/search tool and mentions reranking in the top_k parameter, which is useful. However, it does not describe limitations, result format expectations, or what happens when no relevant fragments are found, leaving some behavioral traits implicit.

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 compact and front-loaded: a clear statement of scope, a direct usage sentence, and concise parameter documentation. Every sentence earns its place, with no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple retrieval tool with an output schema, the description covers the essential context: source books, target topics, query semantics, and return-count behavior. It is slightly incomplete only in not guiding the agent to sibling tools for other medical subjects, but this is a minor gap given the topical clarity.

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. It does: 'query' is explained as a natural-language question about propedéutica, and 'top_k' is clarified as the number of most relevant fragments returned after reranking, including its default value. Both parameters are meaningfully documented 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 uses a specific verb ('Busca') and names the exact resource: books of clinical propedéutica by Argente-Álvarez, Surós, and Bates. It also lists concrete topics (semiología, physical exam technique, signs, symptoms, maneuvers), which lets an agent distinguish it from the sibling subject-specific 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 explicitly says 'Úsalo para' followed by a clear set of use cases, giving the agent practical guidance on when to invoke it. However, it does not state when not to use it or explicitly name alternative sibling tools, so it falls short of full routing guidance.

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