Artemisia · Aguas SB

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

Beyond the readOnlyHint=true annotation, the description adds crucial behavioral details: it is the only tool that consumes model, it does not send anything ('no envía nada'), it provides no prices except published ones, and it responds with links to aguassb.com. These are meaningful disclosures not present in annotations. No contradiction found.

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, but it is front-loaded with the critical 'ÚLTIMO RECURSO' warning, then lists the alternative tool and its inputs, then describes the tool's function and constraints. While not overly concise, every sentence adds necessary context for a tool that is a fallback, justifying the length. The structure could benefit from bullet points but remains readable and logically ordered.

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 2 parameters, no output schema, and sits among 4 siblings, the description is remarkably complete. It covers when to use, what it does, what it returns (links to published content), constraints (no sending, no prices), and the domain of expertise. An agent has all the information needed to invoke it correctly and route to it appropriately.

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% for both parameters (pregunta and idioma) with clear descriptions. The description adds context about the types of water-related questions (consumo, residual, reutilizacion, aridos) but this guides the content of 'pregunta' rather than clarifying the parameter syntax or constraints. Since the schema already documents the parameters fully, a baseline 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?

The description clearly states the tool queries Artemisia, the AI assistant of Aguas SB, and returns content published on aguassb.com. It explicitly distinguishes itself from the sibling obtener_conocimiento by being the last-resort tool that consumes model. The verb 'consultar' and resource 'Artemisia' are specific, and the scope (water treatment domains) is enumerated.

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 explicitly gated: it is the LAST RESORT, to be used only after calling obtener_conocimiento with specific water-type categories, and only when those documents fail or for English responses. It also notes it handles English questions. This is clear when/when-not guidance with named 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation context: it is free, uses reviewed public material, and will not supply design rules or unpublished prices. No contradiction with the annotations exists.

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 opening 'PRIMERA OPCIÓN, sin coste' is front-loaded and immediately actionable. The rest of the description is dense but purposeful: scope, content, limitations, and safety are each covered in a compact form. The 'para que la IA...' clause is slightly meta but still useful for an agent deciding when to invoke the 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?

For a read-only retrieval tool with a simple required enum, an optional filter, and a defaulted boolean, the description provides enough information to select and invoke it correctly. It specifies public scope, cost, content topics, and exclusions. The main missing detail is the exact return shape or pagination behavior, but that is minor given no output schema and the simple nature of the call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67%, so filtro and incluir_metodo are already semantically documented. The description adds some context by linking tipo_de_agua to the document topics, but it does not explain the enum values ('consumo', 'residual', 'reutilizacion', 'aridos') or how to choose among them. This is adequate baseline behavior, not substantial compensation.

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 names the exact resource ('documentos públicos de Aguas SB') scoped by water type. It also positions the tool as 'PRIMERA OPCIÓN, sin coste' and 'Solo consulta', making its read-only knowledge-retrieval role clear. It stops short of a 5 because it never names a sibling tool as an alternative, so part of the differentiation is left to context.

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?

'PRIMERA OPCIÓN, sin coste' gives an explicit default selection rule, and 'sin reglas de diseño ni precios no publicados' draws a clear content boundary for when this tool is not the answer. It is strong contextual guidance, though it does not explicitly say which sibling to use instead in 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?

Annotations already declare readOnly/idempotent/non-destructive behavior, and the description adds value by stating 'Determinista, sin IA' and describing the informational content returned (treatment decision, offer, data to provide, follow-up page, calculation tool). This is useful context beyond the annotations, though it does not detail response format or failure 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 compact and front-loaded: it names the input condition first, then lists the returned guidance, then flags determinism and read-only nature. Every clause contributes, 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 two-parameter, read-only orientation tool, the description covers what the tool does and what the response will contain. Although there is no output schema and the exact return structure is not specified, the described output scope and safety annotations leave the agent with enough context for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented in the schema, including the enum meanings and the privacy note for descripcion. The description adds only a high-level mapping ('para un tipo de agua') and no parameter-level semantics beyond that, matching the baseline for fully covered schemas.

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 ('orientar') with a concrete resource (a water case by water type) and spells out what the tool returns. It is clear and self-contained, but it does not explicitly differentiate itself from sibling tools such as consultar_aguas_sb or procedimiento.

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 opening 'Para un tipo de agua' gives a clear triggering context, and 'Solo consulta' implies a read-only orientation use. However, there is no explicit when-to-use vs. when-not-to-use guidance or mention of alternatives among the siblings, so usage is left to inference.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds valuable context by explicitly stating it does not send anything, does not handle personal data, and returns the text and the URL—information that goes beyond the 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 two sentences with no redundant words. It front-loads the main action and immediately clarifies non-behaviors, making it highly efficient and scannable.

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 drafting tool with only two parameters and no output schema, the description covers the core behavior and privacy constraints. However, it omits any explanation of the parameters (especially 'tipo_de_agua') and does not clarify when to use it relative to siblings, leaving some gaps for an agent to infer.

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 50%—only 'descripcion' has a description, while 'tipo_de_agua' only has an enum without explanation. The tool description does not mention or clarify either parameter, so it fails to compensate for the incomplete schema, leaving the agent without guidance on what values like 'consumo' or 'residual' mean.

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 drafts the text of a water study request for Aguas SB based on the case, and returns the text plus the form URL. It explicitly distinguishes itself by noting it does NOT send anything or handle personal data, setting it apart from siblings like consultar_aguas_sb or orientar_caso_agua.

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 this tool is for drafting a study request when the user has a case description, but it does not explicitly state when to use it versus the sibling tools, nor does it provide exclusions or alternative routes. The context is clear but the guidance on selection is minimal.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint safety. The description adds value by clarifying that the tool provides general orientation and does not actually process or execute the procedure, which is useful operational information beyond the structured 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 compact sentences convey purpose, scope, all options, legal context, and a disclaimer with no redundancy. The front-loaded phrase 'Paso a paso de un trámite habitual en España' immediately establishes the tool's function.

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 read-only, idempotent tool with a single enum parameter and no output schema, the description is complete: it states what the user gets, the geographical scope, the covered topics, and that the tool does not perform real transactions. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden of explaining the one parameter. It enumerates all four enum options in natural Spanish with helpful elaborations, such as 'alcantarillado o cauce' for discharge authorization. It does not provide exact enum code mappings, but the single parameter makes this easy to infer.

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 this tool provides step-by-step guidance for common water procedures in Spain and lists four concrete use cases. It does not explicitly name or differentiate from sibling tools, but the 'no tramita' caveat helps separate it from processing-oriented 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 usage context is implied: use this tool when the user asks about the listed procedures such as discharge authorization, public information about a treatment plant, or water analysis. It does not explicitly state when to prefer a sibling tool or provide exclusion criteria beyond 'no tramita'.

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