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

With no annotations, the description carries the full burden and does well: it discloses that search ignores accents and capitalization, that offsets enable targeted reading, and that hay_mas signals truncation. It does not mention access/permission requirements or result-size limits beyond max_matches, but for a read-only lookup this is solid disclosure.

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 front-loaded: purpose and usage come first, followed by Args and Devuelve blocks. The text is longer than average but nearly every line carries usable information; the Args/Devuelve headers make it 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?

No output schema exists, yet the description enumerates the return shape (ok, id, url_web, total_caracteres, matches[].{offset, extracto}, hay_mas), so an agent can chain calls to texto_completo without guessing. Combined with full parameter documentation, 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%, and the description fully compensates: it documents all four parameters with meaning, accepted ranges and defaults (contexto 50-500 default 200; max_matches 1-25 default 10), the id format example ('H1385488'), and that texto is 1-8 words.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource+scope: search a word/phrase DENTRO del texto completo de una norma (not across norms), returning each occurrence with its offset. It is clearly distinguishable from siblings such as buscar_normas (search across norms) and buscar_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?

Gives an explicit use case and workflow: 'Ideal para saltar a secciones concretas... sin leer todo el texto', and names the companion tool texto_completo(id, offset=X, max_chars=N) for reading around a hit. It lacks an explicit when-not statement (e.g. use buscar_normas when you don't know the id), which keeps it from a 5.

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 this description carries the full burden, and it delivers: it discloses that the SPIJ index ignores 'tomo' (verified), that 'organismo' filters locally by scanning up to 5 pages, that internal page scanning happens per returned page, and the fallback fields ('sugerencias', 'organismos_disponibles'). That is unusually rich behavioral disclosure about partial results and limitations.

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?

Front-loads the purpose then organizes the rest into clear Args/Devuelve blocks, and nearly every line conveys actionable information (param syntax, verified limitation, return fields). It is long, but the length is justified by 11 undocumented parameters, keeping it dense rather than padded.

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 no output schema, the Devuelve block explains the return shape (ok, total, organismo, escaneadas, filtrados, siguiente_start, and conditional sugerencias/organismos_disponibles) and points to detalle_norma/texto_completo for full text. Combined with per-parameter guidance, an agent has everything needed to invoke and interpret this 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 0% across 11 parameters, so the description must compensate – and it near-fully does. Every parameter is documented: consulta query syntax (implicit AND, no OR/quotes, '*' wildcard, start with 1-2 words), tomo, materia, organismo matching behavior, numero format, date range format, orden codes, start/paginas, and sumilla_chars limit semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Busca jurisprudencia en el SPIJ') and the parenthetical '(TC, cortes, precedentes, sentencias)' scopes exactly what kinds of documents are returned. This cleanly separates it from the norms-oriented siblings such as buscar_normas and buscar_en_norma.

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?

Gives strong operational guidance: warns that 'tomo' is sent but NOT applied at index level, and explicitly calls 'organismo' 'la via correcta' for filtering, plus routes to listar_filtros for materias values. It lacks an explicit statement of when to prefer this tool over buscar_normas/buscar_en_norma, so it is clear context rather than full when/when-not framing.

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

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

With no annotations, the description carries the full burden and does disclose real behavior: implicit AND over all words, no quotes or OR allowed, trailing wildcard support, partial-value resolution for 'dispositivo' returning candidates when ambiguous, the indexing gap where some laws surface only as referencing documents, and the nota/sugerencias fallback on zero results. It omits any auth/permission or rate-limit context, which for a public search corpus is a minor 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?

Front-loads the one-line purpose, then a dense Args block and a Devuelve block; nearly every line earns its place given the 0% schema coverage. It is long, but the length is driven by real per-parameter quirks rather than padding, so only marginally verbose.

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?

No output schema exists, and the description fully covers the return shape (ok, total, desde, hasta, siguiente_start, the norms record fields, sumilla_total truncation) plus the zero-result nota/sugerencias structure. An agent has everything needed to call it and interpret the response 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 and it does: every one of the 12 parameters is documented with format and semantics (free-text syntax rules, number without 'Nº' prefix, AAAA-MM-DD dates, orden codes 1-4, start as a multiple of 10 with the (N-1)*10 formula, paginas cap of 10). This is meaning the schema alone could never convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with its corpus: 'Busca normas legales en el SPIJ (normas generales, administrativas, etc)'. That immediately separates it from buscar_jurisprudencia and from within-document tools like buscar_en_norma, and it explicitly points to two siblings (listar_filtros, detalle_norma) for adjacent needs.

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?

Gives concrete operating guidance: start with 1-2 words, use detalle_norma(id) for the full sumilla, and consult listar_filtros when 'dispositivo' is ambiguous. It does not explicitly state when to prefer this over buscar_jurisprudencia or buscar_en_norma, so routing between the closest siblings 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?

With no annotations, the description carries the full burden, and it discloses meaningful behavior: text is returned as plain text without HTML, truncation is signalled via texto_truncado/siguiente_offset, and a url_web is provided for opening in SPIJ. It does not cover auth requirements, rate limits, or error behavior, which are the remaining gaps.

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?

Organized into Args / Devuelve / Nota sections and front-loaded with the core purpose. The paging mechanism is restated across max_chars, siguiente_offset, and the closing Nota, which is mild redundancy but aids readability rather than harming it.

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?

No output schema exists, yet the description enumerates the returned fields (ok, id, url_web, codigoNorma, texto, total_caracteres, siguiente_offset, etc.) and explains the pagination contract, so an agent can consume the result correctly. Missing only ancillary details like permissions or failure modes.

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, and it does: every one of the four parameters is explained with meaning beyond its type — id with format example and provenance, offset (0 = start), max_chars (0 = default) with the truncation contract, and desde_final with the rationale for the 'RESUELVE' tail case.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Devuelve los METADATOS y el TEXTO de una norma del SPIJ por su id'), so the agent knows exactly what it returns. It does not, however, distinguish itself from overlapping siblings such as texto_completo or estructura_norma, which likely also surface norm content.

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?

Gives clear operating context: the id comes from buscar_normas, long texts should be read by ranges with offset, and the tail can be fetched with desde_final for judicial decisions where 'RESUELVE' sits at the end. It stops short of explaining when to choose this over the overlapping siblings (texto_completo, estructura_norma).

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 load, and it does so well: it discloses the return payload (ok, id, url_web, fuente, total_caracteres, encabezados), pagination (hasta 150 with siguiente_encabezado), and the edge case of empty encabezados. It does not explicitly state read-only semantics or auth requirements, which is the only 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?

Front-loaded with the core purpose, then clearly sectioned into Args and Devuelve. Slightly verbose, but essentially every sentence (pagination limit, offset canonical alignment, empty-headers fallback) 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?

With no output schema and no annotations, the description fully specifies the return fields, the pagination behavior, the offset semantics, and the degenerate case. An agent has everything needed to call it and to act on the result.

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

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

Schema coverage is 0% and the single parameter 'id' has no schema description, but the description compensates by giving the format ('ej H1453062') and provenance ('lo dan buscar_*'), which is meaningfully more than the schema alone provides. Only one param, so little else 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?

States a specific verb and resource ('Devuelve el INDICE de encabezados de una norma del SPIJ') and immediately qualifies scope with the offset mechanism. This clearly distinguishes it from siblings like texto_completo and detalle_norma, which an agent can tell apart without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It not only says what it returns but routes the agent: use this to get offsets, then call texto_completo(id, offset=X, max_chars=N) to read specific sections. It also names a fallback (buscar_en_norma or reading by ranges) for norms with no headers such as TC sentencias. Explicit when-to-use and alternative paths.

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 discloses the return shape (dict with 'ok' and a 'valores' list), the default behavior when no category is given, and the caveat that 'sectores' has hundreds of entries. It does not explicitly state read-only/harmless nature, but for a pure lookup tool the disclosed behavior is nearly complete.

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?

Front-loaded with purpose, then organized into Args/Devuelve. Slightly long and the per-category definitions partially restate the earlier list, but every block earns its place by naming example values an agent needs.

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?

No output schema exists, so the description must explain returns — and it does ('valores' are the exact strings accepted by the sibling search tools). With both params documented, the omission default covered, and the sectores fallback given, nothing needed to call it correctly 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 coverage is 0% and neither param has an enum, yet the description supplies the five allowed categoria values, explains the conditional relationship (tomo only applies to categoria='materias'), and gives example values. This fully compensates for 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?

Starts with a specific verb+resource: 'Lista los valores validos para los filtros del SPIJ'. It also ties the output to its consumers, naming the sibling tools (buscar_normas, buscar_jurisprudencia) whose accepted strings these are, so an agent can place it in the workflow immediately.

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 what happens when categoria is omitted (returns a summary with counts and examples), that 'materias' requires 'tomo', and offers a concrete alternative when a sector is missing ('escribe parte del nombre en buscar_normas y se resuelve automaticamente'). This is exactly the when-to-use/when-not guidance the dimension asks for.

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 substantial work: it discloses the two-path retrieval (primary word-document route, fallback to detail text), the pagination model (total_caracteres, texto_truncado, siguiente_offset), and the desde_final shortcut. It does not state permissions, rate limits, or cost, but read-only behavior is clearly implied by 'Devuelve'.

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?

Front-loaded with the purpose, then organized into clear 'Args' and 'Devuelve' sections. Some prose is chatty in Spanish, but every line conveys operative information (fallback logic, truncation, the RESUELVE hint) rather than filler.

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

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

There is no output schema, so the description must explain return values, and it enumerates them precisely (ok, id, url_web, codigoNorma, fechaPublicacion, dispositivoLegal, texto, total_caracteres, texto_truncado, siguiente_offset). For a paginated full-text retrieval tool this is complete enough for an agent to call it 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 fully and it does: 'id' includes the format example 'H1352213' and its source; 'offset' is defined as the starting character; 'max_chars' explains the 0=default sentinel; 'desde_final' is fully explained with a motivating example. Every parameter is documented beyond the bare schema types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Devuelve el TEXTO COMPLETO de una norma o jurisprudencia del SPIJ'. It also discloses the retrieval strategy (SPIJ word document with fallback to detail text), which distinguishes it from metadata-oriented siblings like detalle_norma and estructura_norma.

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?

Gives useful operational context: 'id... lo dan buscar_*' and a concrete use case for desde_final ('en sentencias judiciales la decision RESUELVE esta al final; combinado con max_chars=3000 la lees directo'). However it never states when to choose this tool over siblings such as detalle_norma, estructura_norma, or buscar_en_norma, leaving the routing to inference.

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