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

The annotations already establish that this is a safe, read-only, idempotent, non-destructive operation. The description adds useful behavioral context by listing the returned categories (state, folder, permissions, active protections), which helps the agent understand what information the tool surfaces beyond generic safety metadata.

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

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

The description is a single, front-loaded sentence with no filler. Every listed item (state, folder, permissions, active protections) contributes to telling the agent what the tool returns.

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 parameterless, read-only diagnostic tool with rich annotations, the description is adequate but not complete. It lists return categories without explaining what 'local state' means, how the data is structured, or when the tool should be invoked, and there is no output schema to compensate.

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

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

The tool takes zero parameters, so there are no parameter semantics to explain. Per the scoring baseline for parameterless tools, a 4 is appropriate even though the empty schema fully covers the input structure.

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

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

The description states a clear retrieval verb ('Devuelve') and names specific return categories: state, folder, permissions, and active protections. It does not explicitly differentiate itself from the file-management siblings, but none of them are similarly scoped diagnostic tools.

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

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

The description gives no guidance on when to use this tool versus alternatives. It neither states a use case nor names sibling tools or conditions for selection, leaving the agent to infer usage from the tool name alone.

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 annotations already indicate this is a non-read-only, non-idempotent, non-destructive, closed-world operation. The description adds some behavioral context by mentioning verification of limits, links, and integrity, but it does not explain overwrite behavior, permission requirements, or how confirmar/aprobacion_id affect execution.

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 definition is a single front-loaded sentence with no filler or redundancy. It is appropriately sized, though the brevity contributes to the gaps in other dimensions.

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 four-parameter mutation tool with 0% schema description coverage, no output schema, and an approval parameter, the description is too sparse. It omits confirmation/approval semantics, overwrite behavior, and return-value expectations, leaving the agent with insufficient operational context.

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 carry parameter meaning, but it does not name or explain any of the four parameters. It only implies a source and destination concept, leaving confirmar and aprobacion_id entirely unaddressed.

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

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

The description states a specific verb (copia) and resource (archivo o carpeta completa), plus the target (a una ruta nueva). This clearly distinguishes it from mover_elemento, though it does not name the sibling or elaborate on scope limits.

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

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

There is no explicit guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. The description merely states what the tool does, not when an agent should choose it.

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

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

Annotations already declare write operation (readOnlyHint=false), non-destructive, non-idempotent, and closed-world. The description adds a useful constraint ('No sobrescribe rutas existentes'), but does not explain what happens if the path exists (error? duplicate?), nor mentions the confirmar or aprobacion_id parameters or any confirmation requirements.

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 short sentences with zero waste. The purpose is front-loaded, followed by a key behavioral constraint. Perfectly sized for a simple 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?

With three parameters and no schema descriptions, the description should explain parameter semantics and the approval/confirmation workflow. It omits all of that, and there is no output schema to clarify returns. Incomplete for a tool that likely requires an approval ID.

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

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

Schema description coverage is 0%, so the description must compensate. It does not mention any of the three parameters (ruta, confirmar, aprobacion_id), their formats, or their purposes. The only hint is 'dentro del espacio autorizado', which is vague and insufficient.

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 ('Crea una carpeta nueva') and adds scope ('dentro del espacio autorizado'). Clear what the tool does, but does not explicitly differentiate from siblings like eliminar_carpeta or mover_elemento beyond the obvious name.

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

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

No guidance on when to use this tool versus alternatives. Does not mention prerequisites, when-not to use, or any sibling tool. Only states what it does.

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 destructiveHint=true, and the description usefully qualifies this by clarifying the deletion is recoverable (papelera recuperable) and may create a backup copy. That nuance materially changes how an agent should treat the risk, adding value beyond the raw hint. It still omits the sha256 verification, confirmation, and approval requirements.

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

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

A single front-loaded sentence that states the action and its key behavioral qualifier with zero filler. Well-sized for the operation.

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?

A destructive mutation with an approval-id parameter and a required hash precondition, no output schema, and 0% schema coverage. The description leaves the whole safety/authorization workflow and the meaning of the required hash unexplained, which is a substantial gap 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?

Schema description coverage is 0% with 4 parameters, so the description must compensate and it does not. The required sha256_esperado (an optimistic-concurrency/verification token), confirmar, and aprobacion_id (an approval workflow) are never mentioned or explained.

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: it moves a file to a recoverable trash, not a permanent delete. This distinguishes it conceptually from the removal implied by eliminar_carpeta, though it never names that sibling. Purpose is clear but sibling differentiation is left implicit.

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

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

No guidance on when to use this versus eliminar_carpeta, nor when the trash copy versus backup copy applies. No prerequisites or exclusions are stated. The agent must infer all routing decisions.

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 destructiveHint=true and readOnlyHint=false, but the description adds valuable context beyond them: the deletion is a move to a recoverable local trash and is preceded by content verification. What is missing is any disclosure of the confirmation/approval requirements implied by confirmar and aprobacion_id.

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

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

A single dense, front-loaded sentence that packs the action, scope, and recoverability note without waste. It is efficient, though very terse given the tool's operational complexity.

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 destructive mutation with three undocumented parameters, no output schema, and a required approval identifier, the description omits the confirmation/approval mechanics entirely. Annotations cover safety flags, but the operational workflow an agent needs to call this correctly is absent.

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 three parameters, so the description must carry the burden and largely fails. It never mentions ruta, confirmar, or aprobacion_id, leaving the confirmation and UUID-approval workflow completely unexplained.

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 (mueve/elimina) and resource (una carpeta completa), and clarifies the outcome is a recoverable local trash rather than permanent deletion. It implicitly distinguishes itself from eliminar_archivo by scoping to folders, but does not name or route to that sibling.

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

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

No when-to-use or when-not-to-use guidance, and no mention of prerequisites despite the presence of confirmar and aprobacion_id parameters that clearly gate the operation. The agent must infer the deletion workflow entirely.

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 destructiveHint=false, readOnlyHint=false, openWorldHint=true, but the description does not explain whether existing files are overwritten in ruta_destino, how destination conflicts are handled, or what approval/confirmation entails. 'De forma segura' is vague and not backed by concrete behavior. It adds almost nothing beyond annotations for a mutation 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?

One efficient sentence, front-loaded with the action. It is very short but not wasteful; the problem is what it omits rather than verbosity.

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 4 parameters at 0% schema description coverage, a nested object, no output schema, and a write operation, the description is insufficient. It does not document the expected shape of the 'imagen' object, the confirmation/approval flow, or what happens to an existing destination file.

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% for 4 parameters, including a nested 'imagen' object and optional 'confirmar'/'aprobacion_id'. The description mentions only the image format, adding no meaning to any parameter; a low-coverage schema demands compensation that is absent.

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?

Clear verb+resource: 'Descarga... una imagen... y la crea dentro de la carpeta autorizada', with supported formats (PNG, JPEG, WebP) and source (ChatGPT). It distinguishes itself from file siblings like crear_carpeta or mover_elemento. It does not explicitly differentiate from other write tools, but the niche (saving a ChatGPT image) is clear.

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

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

No guidance on when to use this versus alternatives, and no explanation of prerequisites such as the 'confirmar' or 'aprobacion_id' flow. For a write tool with confirmation parameters, the agent is left to infer when confirmation 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?

With annotations already declaring readOnlyHint/idempotentHint/destructiveHint, the description still adds genuinely useful behavior: reads are chunked at 2 MiB, and the full fingerprint (sha256) can be skipped to avoid traversing large files. That is real context 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?

Two tightly written sentences with no filler, front-loaded with the core action and the size constraint. Efficient, though it leaves no room for the missing parameter meaning.

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 5-parameter read tool with no output schema and zero schema descriptions, the definition is too thin: pagination via offset_bytes, output format via formato, and the base64/texto distinction are never explained, and return shape is unaddressed.

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 full burden, yet it only hints at two of the five parameters (max_bytes via 'hasta 2 MiB', incluir_sha256 via 'huella completa'). ruta, formato, and offset_bytes remain entirely undocumented in both schema and 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?

States a specific verb (lee) and resource (archivos) plus a scoping detail (fragmentos de hasta 2 MiB). The read operation is unambiguous and clearly distinct from the write/delete siblings, though it never explicitly names a sibling it should be preferred over listar_archivos or modificar_archivo.

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 offers no guidance on when to use this tool versus alternatives like listar_archivos, and states no prerequisites (what makes a file 'autorizado'). The chunking detail is a behavioral fact, not usage-direction.

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, and non-open-world, so the safety profile is covered. The description adds genuinely useful traits beyond that – non-recursive traversal and a 500-item ceiling – but omits pagination/truncation behavior (what happens beyond 500) and says nothing about the 'autorizados' permission scope.

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

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

A single front-loaded sentence with no waste, but the brevity tips into under-specification given the undocumented ruta parameter and unclear truncation behavior.

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

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

For a simple read-only listing tool with full annotation coverage, the description covers the essential traversal constraint. However, the only parameter is entirely undocumented and the behavior at the 500-item boundary is unspecified, leaving gaps an agent would hit in practice.

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% for the single 'ruta' parameter, and the description never explains what ruta means, its default (it is optional, so listing presumably roots somewhere), or accepted path formats. With one undocumented parameter, the description fails to compensate for the schema gap.

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

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

States a specific verb (Lista) and resource (archivos/carpetas via the title) with key scope qualifiers: non-recursive and capped at 500. It is distinguishable from siblings like leer_archivo or eliminar_archivo, though the description itself never names an alternative to route between them.

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

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

There is no when-to-use or when-not-to-use guidance and no mention of sibling tools. An agent gets the operational shape (non-recursive, max 500) but no context for choosing this over leer_archivo or listar_copias_seguridad.

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, destructiveHint=false, and openWorldHint=false, covering the safety profile. The description adds only that listed copies are 'recuperables', a useful scoping detail, but does not describe return format, pagination, or what metadata is included.

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

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

A single front-loaded sentence with no wasted words. It communicates the essential action and scope immediately, which is appropriate for a simple listing operation.

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

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

The tool is simple, parameterless, and has comprehensive read-only annotations, so the description is nearly sufficient. However, without an output schema, it could say more about what a listed backup entry contains, such as names or timestamps.

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

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

The tool takes zero parameters, so there are no parameter semantics to document. The baseline for a parameterless tool is 4, and nothing in the description is needed to compensate for schema gaps.

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 ('Lista') and a specific resource ('copias recuperables existentes'), making clear it enumerates recoverable backups. It does not explicitly differentiate itself from sibling listing tools like listar_archivos, but the backup-specific scope is reasonably distinct.

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

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

The description gives no when-to-use guidance, no exclusions, and no alternatives among the many sibling file-management tools. An agent must infer that this tool applies only to backup copies rather than general files.

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 destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered. The description adds one genuinely new behavioral fact – the first call may trigger a local approval request – but says nothing about the confirmar/aprobacion_id flow, reversibility, or what happens to an existing file on overwrite.

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 short sentences, front-loaded with the core action, with no filler. It is arguably too terse for a 7-parameter mutation tool, but as written every sentence carries information.

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 destructive write tool with 7 undocumented parameters and no output schema, the description is far too thin. It omits the approval/confirmation mechanics hinted at by confirmar and aprobacion_id, and gives no sense of what the tool returns or how failure is signaled.

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 7 parameters, so the description must compensate and largely does not. Only the overwrite concept loosely maps to the 'modo' enum; ruta, contenido, formato, confirmar, aprobacion_id and sha256_esperado are left entirely unexplained.

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

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

The description states a specific verb+resource ('crea o sobrescribe un archivo'), which clearly separates it from read/delete/copy siblings such as leer_archivo or eliminar_archivo. It does not explicitly name an alternative, but the create/overwrite scope aligned with the 'modo' enum is 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?

No indication of when to choose this tool over siblings like guardar_imagen_chatgpt or copiar_elemento, nor any prerequisites for use. The only usage-adjacent statement is the approval-request note, which describes a side effect rather than guiding selection.

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

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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false, so the safety profile is covered structurally. The description adds only the move/rename framing and says nothing about overwriting an existing destination, undoability, or the approval flow implied by the schema. Modest added value over 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 short sentences, front-loaded with the core action and then the use cases. No filler, nothing to cut.

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 destructive mutation with no output schema and 4 undocumented parameters, the description is too thin. It omits overwrite behavior, failure modes, and the meaning of the approval parameter, leaving an agent unable to invoke it confidently.

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% for 4 parameters. 'origen' and 'destino' are loosely implied by 'a una ruta nueva', but 'confirmar' and especially 'aprobacion_id' (a UUID suggesting a confirmation/approval workflow) are completely unexplained in both schema and description. A destructive tool hiding an approval parameter is a real gap.

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

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

States a clear verb+resource ('Mueve un elemento a una ruta nueva') and adds the two practical use cases (cut-and-paste, rename). It does not distinguish itself from the close sibling copiar_elemento, so it stops short of 5.

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 mention of 'cortar y pegar o renombrar' implies when the tool is useful, but there is no explicit routing guidance such as when to use this instead of copiar_elemento or eliminar_archivo. Usage is implied, not stated.

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