Boletín Claro

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

Beyond the annotation (destructiveHint: false), the description discloses key behavioral traits: the entry is archived, it enters each client's workflow, and the alert that triggered it is automatically linked. No contradictions with annotations.

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 (three short sentences), front-loaded with the core action, and every sentence adds information. No superfluous words.

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

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

Given the tool's simplicity (2 required parameters, no output schema), the description adequately covers the main aspects: what it does, how to use the parameters, and a prerequisite. It could mention error cases or confirmation, but it is reasonably complete for a straightforward archival action.

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 100%, so baseline is 3. The description adds value by specifying that 'clientes' should be names as they appear in listar_clientes, separated by commas, and 'entrada_id' should be the 'id' field from listar_entradas. This clarifies format and source 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 clearly states the action: 'Archiva una entrada del inbox bajo uno o más clientes', using a specific verb ('archiva') and resource ('entrada del inbox', 'clientes'). It distinguishes from sibling tools like listar_entradas and listar_clientes by defining this as the second filter step, making its purpose 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?

The description indicates when to use the tool: 'es la segunda criba, la decisión de que esa oportunidad es relevante para ese cliente'. It also mentions a prerequisite ('Requiere tener el modo clientes activado'). It does not explicitly state when not to use it or alternatives, but the context is clear enough for an agent to decide.

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?

Beyond the destructiveHint annotation, the description adds that deletion is PERMANENT and IRREVERSIBLE, and includes deleting history (avisos, notas, documentos). No contradiction with annotations.

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?

Single paragraph of 5 sentences, concise and front-loaded. Each sentence adds value: purpose, permanence, two-step process, alternative, and prerequisite. No wasted words.

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 no output schema, the description covers all necessary aspects: action, scope, alternatives, prerequisites, and parameter usage. Fully adequate for a destructive tool with multiple steps.

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 100%. Description adds that 'nombre' must be as in listar_mis_alertas, and clarifies the two-step process with 'confirmar' defaulting to false. Provides meaningful context beyond 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 action: 'Borra una de tus alertas de forma PERMANENTE, junto con todo su histórico'. It specifies the resource (alerta) and explicitly distinguishes from sibling tool 'pausar_alerta'.

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?

Provides explicit guidance: first call with confirmar=false to warn user, then with confirmar=true after confirmation. Also suggests alternative 'pausar_alerta' if user wants to keep history. States requirement of iniciar sesión.

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

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

Annotations declare readOnlyHint=true, and the description adds behavioral context: no login required, returns structured results (boletín, fecha, lugar, enlace). No contradictions. Credit for clarifying auth requirements and output format beyond annotations.

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 with core purpose, but the long first sentence could be split for readability. No excess words, every sentence adds value.

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?

Despite no output schema, the description explicitly states what each result contains (boletín, fecha, lugar, enlace). Covers input constraints (optional parameters, defaults, natural language query). Complete for an agent to use effectively.

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 100%, but the description enriches each parameter: explains 'tipos' as optional codes (BOE, BOJA, DOGC), gives range for 'limite' (1-25, default 10), and describes 'consulta' as natural language with concrete examples. This goes well beyond the schema definitions.

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 Spanish official gazettes (BOE, BORME, regional) for anything except grants and tenders, distinguishing it from the sibling tool 'buscar_oportunidades' which handles those exclusions. Examples like 'normativa, oposiciones, anuncios' make the purpose concrete.

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?

Explicitly tells when to use (non-grant/non-tender searches) and when not to ('Para subvenciones o licitaciones usa buscar_oportunidades'), providing a direct alternative. This eliminates ambiguity.

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?

readOnlyHint annotation already indicates read-only; description adds what is returned (NIF and total money). No contradiction. Does not mention edge cases like no results or errors, but sufficient for simple 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?

Two sentences, no wasted words. Front-loaded with purpose, then usage guidance. Highly 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?

Covers purpose, usage, return fields, and authentication. Lacks mention of pagination or no-match behavior, but acceptable for a simple search tool without output 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?

Schema coverage is 100% and description repeats 'Nombre o parte del nombre' from schema. Adds no new parameter details, but explains overall tool behavior with the parameter, meeting baseline.

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?

Specifically states it searches for companies by name (or part), returns NIF and total public money received, and is used as a precursor to perfil_empresa. Differentiates from siblings by clarifying when to use vs. NIF-based 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?

Explicitly states use case (user mentions company by name, not NIF) and workflow (choose one to consult detail). Includes no-login requirement. Lacks explicit exclusion of alternatives, but implication is clear.

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

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

Annotations already declare readOnlyHint=true, so agent knows it's safe. Description adds that no login is required and specifies return fields (importe, plazo, lugar, enlace), providing useful behavioral context beyond annotations.

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?

Description is well-structured and front-loaded with the main purpose. Every sentence adds value, though it could be slightly more concise. No wasted words.

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

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

With 5 parameters and no output schema, the description fully explains return format, parameter usage, and prerequisites. It covers all aspects needed for an agent to invoke 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 has 100% description coverage, but the description adds meaningful context for all parameters: explains 'tipo' values, 'zona' format, 'limite' default/range, 'consulta' with example, and 'incluir_cerradas' with usage scenario.

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 open grants and public tenders matching a company profile in natural language. It is distinguished from sibling tools like perfil_empresa and detalle_convocatoria, and explicitly calls itself 'la herramienta estrella' for such queries.

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?

Provides explicit when-to-use guidance, including parameter-specific advice for 'incluir_cerradas' (historical/study) and redirects to sibling 'perfil_empresa' for won contracts. Also suggests creating alerts for ongoing monitoring.

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

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

Annotations only provide destructiveHint=false. Description adds important behavioral context: the two-step confirmation process, natural language input requirement, and login prerequisite. No contradiction with annotations. Could mention return value but still strong.

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 sentences covering purpose, concept, and usage instructions. Front-loaded with main action. Could be slightly more concise, but no unnecessary words. Well-structured for agent 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?

Tool has no output schema, so description should explain return value (e.g., alert ID). It does not mention what the response looks like. However, it covers workflow and prerequisites adequately. Missing output expectation lowers completeness.

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 100%, so baseline 3. Description adds value by explaining confirmar parameter's role in the two-step process and providing examples for descripcion, which aids agent in crafting proper input beyond 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 creates an alert for monitoring public money, with a specific verb 'crea' and resource 'alerta'. It distinguishes from siblings by explaining it transitions from one-time search to continuous monitoring, unlike editing or deleting alerts.

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?

Explicitly instructs to call first with confirmar=false to show a summary, then with confirmar=true only after user confirmation. Also mentions prerequisite of having logged in. Provides clear when-to-use guidance.

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

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

Annotations only indicate non-destructive. Description adds that login is required and that failure occurs if client mode is not active. No contradiction. Provides useful behavioral context beyond annotations.

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 sentences: front-loaded with action, then conditions. No redundant words, every sentence adds value.

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 simple tool with one parameter and no output schema, the description covers purpose, parameter, prerequisite, and error condition. Lacks return value description but is fairly complete for its simplicity.

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 100% with a clear description and example for the sole parameter 'nombre'. The description only mentions 'Toma 'nombre'.' without adding extra meaning, so baseline score of 3 is 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?

Clearly states the tool creates a new client (company/organization) and explains the purpose (to archive entries under it). Distinguishes from siblings like 'listar_clientes' and 'buscar_empresa'.

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?

Indicates when to use (to create a client in client mode) and includes conditions (requires login, client mode activation). Could be improved by explicitly stating when not to use or suggesting alternatives, but the context is clear.

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

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

Annotations provide readOnlyHint=true; the description adds that no session is needed and specifies returned fields (organismo, importe, etc.), going beyond annotations.

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?

Two sentences front-loaded with the main purpose, concise with no unnecessary words.

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 low complexity (1 param, no output schema), the description completely covers the tool's purpose, input source, output contents, and login requirement.

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 100% schema coverage, the description adds meaning by explaining the code comes from the /concesiones link from buscar_oportunidades, enhancing the schema's 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?

The description clearly states it returns the complete detail of a single grant call (convocatoria de subvenciones BDNS) given its code, distinguishing it from siblings like detalle_licitacion and buscar_oportunidades.

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 'Use it to summarize a grant without leaving Boletín Claro' and notes the code comes from buscar_oportunidades. It also clarifies no login is required, but does not mention when not to use or alternative 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?

Annotations already declare readOnlyHint=true. The description adds that no login is required, which is useful. However, it does not disclose potential error handling or data freshness, but given the annotations cover the safety profile, the description adds moderate value.

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 dense paragraph that front-loads the main action and input method, then lists return fields and usage recommendation. It could be more structured with bullets but is concise and without 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?

Given no output schema, the description lists expected return fields and mentions conditional data (adjudicatarios if awarded). It also provides usage context and input alternatives. Missing differentiation from detalle_convocatoria, but overall adequate for a detail tool.

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 baseline is 3. The tool description restates the input options but does not add significant new meaning beyond what the schema already explains (e.g., source of id and recommended usage).

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 ('Devuelve') and clearly identifies the resource ('detalle completo de UNA licitación pública'). It lists the exact fields returned, distinguishes input methods, and implicitly differentiates from sibling tools like buscar_oportunidades by referencing it as the source of the id.

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 when to use the tool ('para resumir o comparar licitaciones sin abrir el portal oficial') and notes that no login is required. It provides clear guidance on input alternatives (id recommended) but does not mention when not to use it or differentiate from similar sibling like detalle_convocatoria.

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

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

Annotations provide destructiveHint, and the description adds that changing the description rebuilds the search criterion and requires confirmation. It also notes login requirement. No contradictions exist.

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 and front-loaded, starting with the main action. Every sentence contributes meaningful information without redundancy.

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 4 parameters, no output schema, and destructive annotations, the description covers the confirmation process, effects of changes, and login requirement. It is complete for the tool's complexity; return value is not detailed but acceptable without output 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?

Schema coverage is 100%. The description adds value by explaining the effect of 'nueva_descripcion' (rebuilds criterion), the role of 'confirmar' (mandatory for description change), and that 'nombre' refers to the current name from 'listar_mis_alertas'.

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 edits an alert, changing its monitored query or name, identified by current name. It uses specific verbs and resource, distinguishing it from siblings like 'borrar_alerta' or 'crear_alerta'.

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 explains when to use (login required, to edit alerts) and provides a detailed confirmation flow for description changes versus renaming. It does not explicitly state when not to use or name alternatives, but the sibling list and context are clear.

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

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

Annotations indicate readOnlyHint=true, and the description adds that it requires 'modo clientes' to be activated and returns alerts alongside clients. This goes beyond the annotations by disclosing a precondition and additional output content.

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 two sentences that efficiently convey purpose, context, and usage. No wasted words.

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 an output schema, the description explains that it returns clients and their alerts, and includes a prerequisite. This is complete for an agent to decide when to use the tool.

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 no parameters, so schema coverage is 100%. The description adds no parameter details, but the baseline for 0 parameters is 4, and no further explanation is needed.

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 lists clients along with their alerts, specifying the context (modo clientes, para asesorías y gestorías). It distinguishes from siblings like 'crear_cliente' and 'asignar_entrada' by focusing on listing clients before assignment.

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 to use it for '¿qué clientes tengo?' or before assigning entries, providing clear context. It does not explicitly exclude other scenarios, but the guidance is sufficient for typical usage.

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 description adds behavioral details beyond the readOnlyHint annotation: it states the tool requires 'modo clientes activado' and specifies default and maximum limit. It accurately implies read-only behavior by describing it as returning the inbox.

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: two sentences cover purpose, workflow integration, and sibling references, followed by a clear parameter note. It is front-loaded with the core functionality and avoids redundancy.

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

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

Given the tool has 2 optional parameters, no output schema, and many siblings, the description is complete. It explains the return type (inbox entries), integration with 'asignar_entrada', required mode, and parameter defaults, leaving no critical gaps for a tool of this 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?

Both parameters are fully described in the schema (100% coverage). The description adds value by specifying defaults and constraints: 'limite' defaults to 25 and max is 60, and 'alerta' filters by alert name. This enhances understanding 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 clearly states the tool returns inbox entries that match alerts but are not yet archived under any client. It distinguishes itself from sibling tools like 'asignar_entrada' (assignment) and 'listar_clientes' (client context), making its purpose 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?

The description explains when to use this tool: as the first filter after alerts, to review entries before assigning them. It mentions prerequisites ('modo clientes activado') and references sibling tools for context, though it doesn't explicitly list cases where this tool should be avoided.

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 readOnlyHint annotation already indicates a safe read operation. The description adds specific behavioral details about the return fields (active status, frequency, newsletters, processing state), which is valuable beyond the annotation. No contradiction.

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 sentences, concisely stating what the tool does and when to use it. It is front-loaded with the key verb 'Lista' and lists the return fields without unnecessary detail.

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

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

The output schema is absent, so the description must explain return values. It does so thoroughly by listing the fields: active status, frequency, newsletters, and up-to-date/pending state. For a parameterless list tool, this is 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 input schema has zero parameters and schema coverage is 100%, so the description does not need to explain parameters. Baseline for 0 parameters is 4, and the description adds no parameter info beyond what's structured.

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 lists the user's thematic alerts and their status (active, frequency, newsletters, up-to-date or pending). It provides example queries, making the purpose unambiguous. It distinguishes from sibling tools like crear_alerta or editar_alerta, which perform other actions.

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 gives use cases: '¿qué alertas tengo?' or '¿están funcionando mis alertas?'. This helps the agent know when to invoke this tool. However, it does not explicitly state when not to use it or suggest alternatives, but the context is clear given the sibling 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?

Annotations already declare readOnlyHint=true, and the description adds behavioral details: returns opportunities filtered by alerts, with specific fields and optional parameters with defaults. No contradictions.

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 sentences plus parameter details, efficiently stating purpose, usage examples, and parameter info. No unnecessary words.

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 what the tool returns (including fields) and how parameters work. Since there is no output schema, describing the output fields is important. Missing details like sorting order or pagination beyond limit, but defaults and max values are given.

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 100% with clear descriptions for both 'dias' and 'limite'. The description repeats this information without adding new meaning beyond the defaults, so it does not significantly enhance comprehension 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 clearly states it returns recent news matching the user's alerts, specifying fields (boletín, fecha, importe, plazo, enlace). Differentiates from sibling tools like buscar_oportunidades by focusing on alerts.

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?

Provides explicit usage examples ('¿qué me ha llegado?', '¿hay algo nuevo en mis alertas?') and mentions optional parameters. Does not explicitly state when not to use or list alternatives, but the context sufficiently guides usage.

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

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

Annotations indicate destructiveHint=false. Description adds that it does not delete (pauses only), is reversible, and requires login. No contradictions.

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 sentences, each with a clear purpose: action/effect, parameter guidance, and additional context (reversibility/login). No wasted words.

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

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

Given the tool's simplicity (one required parameter, no output schema, low complexity), description covers all needed aspects: purpose, parameter source, reversibility, login requirement. 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 coverage is 100%, so baseline is 3. Description adds value by specifying that the parameter should match the name from listar_mis_alertas, providing beyond-schema 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?

Description clearly states 'pausar' (pause) one's alert to stop notifications without deleting. It uses a specific verb and resource, and differentiates from sibling tools like borrar_alerta (delete) and reactivar_alerta (reactivate).

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?

Explicitly indicates when to use (to stop notifications without deletion), provides alternative (reversible with reactivar_alerta), and gives guidance on parameter value ('tal como aparece en listar_mis_alertas'). Also mentions login requirement.

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

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

Annotations indicate readOnlyHint=true, and the description confirms this by stating it returns aggregated data without modifying anything. It further adds useful context like the sources, the type of output (aggregates plus a link), and that no authentication is needed, which are not fully captured by annotations alone.

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 relatively long but every sentence carries important information: main purpose, use cases, limitations, and prerequisites. It is front-loaded with the core functionality. While it could be slightly more compact, it remains well-structured and avoids redundancy.

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

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

Given the tool has only one parameter and no output schema, the description provides comprehensive coverage: it explains what data is returned (aggregates from multiple sources), the output format (link to profile, not list), and the scope (no login needed). It fully compensates for the lack of an output 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 schema already provides a description for the 'nif' parameter, achieving 100% coverage. The description adds extra value by instructing the agent to use 'buscar_empresa' if only the company name is available, which is beyond the schema. However, the schema description itself is sufficient, so the added value is moderate.

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 begins with a clear verb 'Devuelve' and specifies the resource 'perfil de dinero público de una empresa (por NIF)'. It lists multiple data sources and distinguishes itself from sibling tools like 'buscar_empresa' by explicitly stating that it returns aggregated data, not a contract-by-contract list.

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 explicit when-to-use scenarios such as '¿qué licitaciones o contratos ha ganado X?' and when-not-to-use: 'Da agregados y un enlace a la ficha completa, no el listado contrato a contrato.' It also mentions the prerequisite of using 'buscar_empresa' if only the company name is known, and that no login is required.

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

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

Annotations only set destructiveHint=false. The description adds that the tool reactivates (consistent) and requires login, but does not disclose behavior if the alert is not paused, nor any side effects beyond state change.

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?

Two sentences: first states the purpose, second clarifies the parameter and a prerequisite. No wasted words, 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 simple 1-parameter tool with no output schema and minimal annotations, the description covers the core action, parameter source, and a precondition. It could mention what happens if the alert is already active, but overall 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 coverage is 100% with a parameter description. The tool description adds context by explaining where to find the parameter value ('tal como aparece en listar_mis_alertas'), which goes 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 clearly states the action: reactivating a paused alert to resume notifications. It uses a specific verb ('reactivar') and resource ('alerta'), and implicitly distinguishes from siblings like 'pausar_alerta' and 'borrar_alerta'.

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 indicates when to use (to reactivate a paused alert) and mentions a prerequisite (login required). It references listar_mis_alertas for the parameter value but does not explicitly exclude scenarios or compare with alternatives like editar_alerta.

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?

Beyond the readOnlyHint annotation, description adds that it returns entries grouped by section with counts, titles, amounts, deadlines, and lists possible source codes. It clarifies it's an index and requires no authentication.

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 paragraph that efficiently covers purpose, examples, parameters, and usage guidance without unnecessary words. Every sentence adds value.

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 tool with good annotations and full schema, the description explains the return format (grouped entries with sample data), parameter usage, and references sibling for deep dive. Complete for its 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?

Schema coverage is 100% with descriptions for both parameters. Description adds value by listing example source codes (BOE, BOCM, etc.) and giving date format example (AAAA-MM-DD).

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 summarizes official bulletins for a specific day, using verbs like 'Resume' and specifying the resource 'boletín oficial'. It provides example queries and distinguishes from sibling tool 'buscar_boletines' which is for details.

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?

Explicitly tells when to use this tool (daily index) and when to use sibling 'buscar_boletines' for details. Also notes no login required, a prerequisite for use.

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

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

Annotations already declare readOnlyHint=true; description adds behavioral context: it groups by alert, uses pre-generated summaries, and covers 'de lunes a hoy' (current week dynamic). No contradictions.

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?

Two sentences: first defines functionality clearly, second provides usage examples. No filler words, every sentence adds value.

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?

Adequately describes purpose and usage. Lacks output format details, but given no output schema and simple nature, it is sufficiently complete for agent 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?

Tool has no parameters, so schema coverage is 100% trivially. Description does not need to elaborate; baseline 4 is 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?

Description clearly states the tool summarizes weekly alert matches grouped by alert, using pre-generated summaries. It uses specific verb 'resume' (summarize) and resource 'semana' (week) with alerts context, distinguishing from sibling 'resumen_boletin' by scope and aggregation.

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?

Provides explicit example queries like 'resúmeme la semana', indicating common use cases. Does not explicitly state when not to use it or compare to all siblings, but the examples effectively guide appropriate usage.

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?

Describes the two-step confirmation process (confirmar=false then true), authentication requirement, and paid nature. Annotations only provide destructiveHint=false, and description adds significant behavioral context without contradiction.

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?

Well-structured with clear topic sentence, differentiation, parameter details, and workflow. Slightly long but every sentence adds value.

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?

Covers purpose, usage, parameters, behavior, prerequisites. No output schema, but description is self-sufficient for agent to use 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?

Adds meaning beyond schema: explains empresas can be names or NIFs, separated by commas, and describes the two-step use of confirmar.

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 creates surveillance of specific companies, watching for public money movements. It distinguishes from sibling tool crear_alerta for topics.

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?

Explicitly says when to use this vs crear_alerta, mentions it's a paid function and requires login.

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