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

With no annotations, the description carries the full burden of behavioral disclosure. It hints at resolving and synchronizing a persistent revision, which implies state mutation, but provides no details on permissions, side effects, reversibility, or what happens when the element is already open.

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 short sentence with no wasted words, and the core action 'Abre un elemento' is front-loaded. However, the trailing clause 'resuelve y sincroniza la revisión persistente' is jargon-heavy and does not earn its place without further explanation.

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 state-changing tool with no annotations, no output schema, and an undocumented parameter, the description is far too sparse. It omits when to use it versus abrir_elemento_sin_resolver, parameter details, side effects, and what 'persistent revision' means 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 parameter nombre_elemento, so the description must compensate. It only implies that 'un elemento' is named, without explaining format, expected values, or constraints for the parameter.

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 verb and resource ("Abre un elemento") but leaves the resource vague—'elemento' is not defined among many element types. It adds 'resuelve y sincroniza la revisión persistente', which is unclear and does not differentiate this tool from the sibling abrir_elemento_sin_resolver.

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 context is given. The description does not mention the alternative abrir_elemento_sin_resolver, nor does it state prerequisites or conditions under which this tool should be chosen over simply opening without resolving.

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 behavioral burden. It usefully discloses that no Solve is run and no workspace file regeneration occurs, which is the key behavioral distinction, but it omits other operational traits such as whether opening mutates state, persistence effects, permissions, or error conditions.

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 wasted words. It places the core action first and the key negative scope second, which is appropriate for a simple one-parameter 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 simple open-element operation, the description covers the crucial 'sin Solve ni regeneración' behavior. However, with no annotations, no output schema, and 0% schema description coverage on the required parameter, it leaves gaps around parameter semantics and usage selection that an agent may need.

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?

There is one required parameter, nombre_elemento, and schema description coverage is 0%; the schema only repeats the title 'Nombre Elemento'. The description does not add any meaning about the expected name format, element identifiers, or valid values, so the parameter remains minimally documented.

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 ('Abre un elemento') and immediately qualifies it behaviorally ('sin Solve ni regeneración de archivo workspace'), which distinguishes it from the sibling abrir_elemento and from regenerar_workspace. An agent can tell what this tool does and what it explicitly does not do from the first sentence.

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 negative qualifiers imply the tool should be chosen when the caller wants to open an element without Solve or workspace-file regeneration, but the description never states when to use it versus abrir_elemento or when not to use it. Usage is inferable rather than explicit.

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 behavioral burden. 'Agrega' implies a mutation, but the description does not state side effects, validation requirements, whether the target bus must already exist, units, permissions, or whether the model is recalculated.

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 single sentence is front-loaded and free of filler, but it is too terse for an 8-parameter mutation tool. The structure is acceptable, but the content is under-specified rather than optimally concise.

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?

An output schema exists, so return values need not be explained. However, given 8 input parameters, no annotations, and 0% schema description coverage, the description is far too incomplete: it omits required parameter meaning, units, defaults, and preconditions for adding a load.

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 has 8 parameters with 0% description coverage, including required fields nombre, bus, and kw plus defaults for kv, kvar, fases, critica, and tipo_visual. The description only vaguely hints at symbol selection and does not document any parameter names, formats, units, or required 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?

States a specific verb and resource: 'Agrega una carga' and adds that it allows choosing the single-line diagram symbol. The purpose is clear, but it does not distinguish itself from nearby siblings such as agregar_linea, agregar_transformador, or configurar_tipo_carga_unifilar.

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 no when-to-use guidance, no prerequisites, and no alternatives or exclusions. The agent is left to infer that this tool should be used whenever a new load is needed on the single-line diagram.

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, so the description carries the full burden. It only implies a mutation ('Agrega') and identifies the model type (OpenDSS Generator), but says nothing about permissions, side effects, reversibility, or whether an existing circuit is required. Thin 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?

A single, front-loaded sentence with no filler. The phrasing 'grupo electrógeno/modelo Generator' is slightly redundant, but overall it is appropriately sized and wastes no 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?

For a 5-parameter mutation tool with no annotations and 0% schema description coverage, the description is far too sparse. While an output schema exists (relieving the need to describe returns), the input semantics, prerequisites, and behavioral expectations are 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% for 5 parameters. The description provides no explanation of what 'nombre', 'bus', 'kw', 'kv', or 'fases' represent or how they should be supplied. It fails to compensate for the total absence of schema descriptions.

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 ('Agrega') and resource ('grupo electrógeno/modelo Generator de OpenDSS'), making it distinguishable from sibling 'agregar_*' tools that target lines, transformers, or loads. It does not spell out that it's a backup generator or its role in the circuit, so it's clear but not richly differentiated.

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 explicit when-to-use guidance, prerequisites, or alternatives. The implied context is that it's part of a model-building sequence, but nothing directs the agent to use it over other element-adding 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?

No annotations are provided, so the description carries the full behavioral burden. It discloses one important side effect—marking the workspace as MODIFICADO—but omits authentication requirements, error behavior, validation rules, and whether the operation is reversible.

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 wasted words. However, it is extremely terse for a tool with 7 parameters and no schema descriptions, making it undersized for the 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?

Given 7 parameters at 0% schema coverage, no annotations, and an output schema, the description should compensate by explaining parameter semantics and usage context. It does neither, leaving the agent without enough information 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?

The schema has 7 parameters with 0% description coverage, and the description mentions none of them. It provides no meaning, format, units, or defaults for parameters such as bus1, bus2, longitud_km, fases, r1_ohm_km, or x1_ohm_km.

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 and resource: añade una línea/cable. It is clear what the tool does, although it does not explicitly distinguish itself from sibling tools such as crear_circuito or agregar_transformador.

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 guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. The only implied context is that it adds a line to the workspace.

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 says nothing: it does not disclose whether the transformer is added to a workspace, whether validation occurs, whether it is rejected on duplicate names, or whether defaults (delta/wye) are applied silently. 'Update/mutate' implications are only inferable from the verb.

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 short sentence, front-loaded and free of waste, but the brevity is under-specification rather than discipline given the tool's 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?

An 8-parameter mutation tool with no annotations and 0% schema coverage leaves the agent without enough to call it correctly. An output schema exists, so return values need not be explained, but the input contract and the professional-sibling choice remain unresolved.

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 8 parameters, and the description mentions no parameter at all. Required fields like kva, kv_primario, bus_primario and the delta/wye defaults are left entirely undocumented; the description does not compensate for the coverage gap in any way.

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 (agrega) and resource (transformador) with two qualifiers: three-phase and two-winding. This distinguishes it from a generic element-adder, but it does not differentiate it from the sibling 'agregar_transformador_profesional', which is the most important ambiguity an agent faces here.

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 guidance and no mention of the near-identical sibling 'agregar_transformador_profesional', whose existence is exactly what an agent needs resolved before choosing. The description gives no context on prerequisites (e.g. needing an active workspace or defined buses).

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 must carry the behavioral burden. It usefully discloses that missing professional fields are filled with silent defaults, which is an important side effect. It does not, however, describe required inputs, persistence behavior, validation, or what happens if the transformer already 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 description is a single front-loaded sentence with no filler. It is concise and directly states the tool's behavior, though its terseness borders on under-specification for a 22-parameter creation 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 complex 22-parameter creation tool with 8 required fields, no annotations, no output schema, and no parameter descriptions, one sentence is insufficient. It omits required parameters, defaulting consequences, and any modeling impact of silently defaulted %Z, X/R, losses, or taps.

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 22 parameters. The description mentions only four field groups (%Z, X/R, pérdidas, taps) and says they may be defaulted silently, leaving most parameters undocumented in both schema and description. It adds some meaning for those few fields but does not compensate for the coverage 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?

The description names a specific verb and resource: 'Crea un transformador P2'. It also states the tool's distinctive scope: fields like %Z, X/R, losses, and taps are omitted and filled with silent defaults. This differentiates it from a generic transformer-creation sibling, though it never names that sibling explicitly.

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 omitting %Z, X/R, losses, and taps 'con defaults silenciosos' implies this tool is for cases where professional data is incomplete. However, there is no explicit when-to-use or when-not-to-use rule, and no named alternative such as agregar_transformador is given.

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 add useful behavioral context: the 3% default is not a universal normative requirement, OpenDSS resolves voltages, and the MCP derives the bus1-to-bus2 comparison over the current revision. It still does not state whether the operation is read-only, what side effects exist, or what the result contains.

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 purpose is front-loaded in a single clear sentence, followed by a short caveat about the default. There is no redundant text, though the second paragraph is a little abstract.

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 one-parameter analysis tool with no annotations and no output schema, the description gives the calculation source and a default caveat. It remains incomplete because it neither explains the return value nor routes the agent relative to the many sibling power-flow and analysis tools.

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 for the single parameter limite_pct. It identifies the parameter as a user-configurable threshold and explicitly gives the 3% default, but it does not state accepted ranges, units beyond percent, or how the limit affects the analysis.

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: 'Analiza ΔV por alimentador', so an agent knows it computes voltage drop per feeder. However, it does not distinguish itself from sibling analysis tools such as ejecutar_flujo_potencia or analizar_flujo_operacion, so sibling differentiation is absent.

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 in the large sibling set. The description explains the default limit's role, but that is behavioral context, not selection 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?

With no annotations provided, the description carries the full burden. It mentions that the tool updates the workspace, which is a useful side effect disclosure, but it does not explain what that update entails, whether it overwrites data, what permissions are needed, or what the returned flow contains.

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 wasted words. It efficiently packs both the return value and the side effect, though it could benefit from slightly more structured 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?

Given no annotations, no output schema, and a mutating side effect, the description is too sparse. It does not explain what 'flujo detallado OpenDSS' includes, how the workspace update affects state, or when this analysis should be preferred over related tools.

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 has zero parameters, so the baseline is 4 per the rubric. The description adds no parameter information, which is appropriate since there is nothing to document.

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 ('Devuelve') and resource ('flujo detallado OpenDSS por alimentador'), plus a side effect ('actualiza el workspace'). It is clear enough for an agent to understand the operation, but it does not differentiate itself from sibling tools like ejecutar_flujo_potencia or analizar_caida_tension.

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 it does, leaving usage context entirely 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 full behavioral burden. It usefully discloses a key side effect ('invalida resultados previos') and the conditional update rule for R1/X1, which is real added value. However it omits permissions requirements, the scope of invalidation, and what the operation returns.

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 with the assignment action front-loaded and no filler. The domain jargon is dense but each sentence conveys distinct 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 4-parameter mutation tool with no annotations, no output schema, and zero schema coverage, the description covers the invalidation behavior well but leaves parameters and permission/return context undocumented. Partially adequate, but gaps remain that an agent must guess at.

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 does not document any of the four parameters (codigo, instalacion, nombre_elemento, actualizar_impedancia). References to 'formación elegida' and R1/X1 updates only loosely hint at instalacion and actualizar_impedancia, leaving the parameters effectively 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 and resource: 'Asigna un conductor de catálogo a Line.*', which is concrete and actionable. It doesn't explicitly differentiate itself from catalog siblings like listar_conductores or obtener_conductor, but the assignment action 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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named for comparison. The note that ampacity 'puede aplicarse de forma independiente' hints at a related path but does not tell the agent when to choose this tool over others.

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; it usefully discloses that the process is deterministic QA and that it yields a gating verdict on emission enablement, which is real behavioral context. It omits whether the call mutates state, what permissions are required, and whether the verdict is persisted.

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 naming the action first and the reported outcome second, with no filler. Nothing is wasted, though it is arguably terse given the missing parameter guidance.

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 1-parameter evaluation tool with no output schema and no annotations, the description covers the purpose and the nature of the result but leaves the parameter undefined and the return shape unexplained. It is minimally adequate rather than 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 single parameter estudios_requeridos has 0% schema description coverage and is never mentioned in the description, so an agent gets no help on what values to supply or whether it is required. The description fails to compensate for the coverage 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 action (deterministic QA execution) and the outcome it produces (whether the model can be enabled for emission), which is clearer than a bare 'audit model'. It does not, however, distinguish itself from closely related siblings such as validar_construccion_rev0 or evaluar_cierre_* , leaving ambiguity about when an audit differs from a validation.

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 statement of when to invoke this tool versus the many validar_/evaluar_/verificar_ siblings, nor any prerequisite (e.g., model must be built first). Usage must be inferred entirely from the name.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure and discloses nothing. It does not state whether the tool is read-only or mutating, what standards or formulas it applies (IEEE 1584 vs. Lee), what units or assumptions govern the computation, or anything about permissions or side effects.

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 single sentence is short but that is under-specification rather than conciseness; it omits every fact an agent needs. There is no front-loading problem because there is essentially no content to order.

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 engineering computation with no annotations and no output schema, the description is completely inadequate. It must at minimum state the calculation performed, the unit conventions, and how it relates to the sibling arc flash tool, none of which is present.

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?

Four parameters (three required) with 0% schema description coverage, and the description supplies no meaning for any of them. Field titles like 'Voltaje Kv' and 'Tiempo Despeje S' are self-evident, but critical semantics such as accepted ranges, the meaning of the 455 mm default, or whether distance is working distance or arc gap are absent from 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?

The description states only that this is a v0.5-compatible alias and never says what the tool does. The name suggests arc flash calculation, but the text adds no verb, no resource, and no differentiation from the obvious sibling estimar_arc_flash_lee. It is a near-tautology that leaves the actual purpose to inference from the tool 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?

There is no guidance on when to use this tool, when not to, or which sibling supersedes it. Given that estimar_arc_flash_lee appears to be the canonical arc flash estimator, the description should explicitly explain the alias relationship and selection rule; it does neither.

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 behavioral burden. It hints at a mutation (resolve + sync persistent revision) but says nothing about whether closing is reversible, what happens to unresolved dependencies, required preconditions, or the effect on the stored revision.

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 short sentence with no filler, and the core action is front-loaded. It is terse rather than padded, though it is arguably too compressed to be informative.

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 one-required-param mutation tool with no annotations and no output schema, the description is too thin: it does not clarify what closing does to the model state, what "revisión persistente" means, or what a caller should expect afterward.

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 has 0% description coverage for nombre_elemento and the description adds no meaning about it (format, identifier type, naming rules). With the one param undocumented in both places, 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 verb and resource ("Cierra un elemento") plus an added effect ("resuelve y sincroniza la revisión persistente"), which distinguishes it loosely from cerrar_elemento_sin_resolver. However, it never names that sibling and never explains what "cerrar" an element actually means in this model context, leaving the purpose only partially resolved.

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, when-not-to-use, or alternative-selection guidance. The implicit contrast with cerrar_elemento_sin_resolver and abrir_elemento is left entirely for the agent to infer from the name.

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

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

With no annotations, the description carries the full behavioral burden. It discloses one negative trait (no Solve, no workspace file regeneration), which is genuinely useful, but says nothing about persistence, validation, side effects, or what 'cerrar' actually does to the model state.

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 compact sentence with no filler. It is front-loaded with the action, though the terseness partly reflects under-specification rather than disciplined editing.

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 an element-lifecycle mutation tool in a large power-systems domain with no annotations, no output schema, and an undocumented parameter, the description is too thin. It omits state implications, error conditions, and how it pairs with abrir_elemento_sin_resolver.

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 parameter nombre_elemento, so the description must compensate and does not mention it at all. The agent gets no hint about the expected identifier format or whether it must match an element previously opened.

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 verb 'Cierra' plus resource 'elemento' is stated, and the qualifier 'sin resolver' hints at a distinction from cerrar_elemento. However, it never says what an 'elemento' is in this domain (circuit, line, load?) or explicitly distinguishes itself from the sibling cerrar_elemento, leaving the agent to infer the difference from the name alone.

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 guidance about when to choose this over cerrar_elemento, or over abrir_elemento_sin_resolver, despite the sibling list containing near-identical names. The description only restates behavior, not selection criteria or preconditions.

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 at all, the description carries the full burden, and it does disclose one meaningful trait: the operation does not touch OpenDSS, implying the simulation model is left intact. It says nothing about persistence, whether prior metadata is overwritten, permissions, or side effects, all of which matter for this configuration call.

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 zero filler, which is structurally efficient. The terseness is arguably under-specification rather than true conciseness, but as written nothing is wasted.

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?

Eight parameters, no annotations, no output schema, and 0% schema description coverage make this a data-mutating configuration tool that the one-sentence description does not adequately cover. An agent cannot know from this text what values are valid, what gets overwritten, or how the change is persisted.

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 8 parameters, so the schema offers only bare titles ('Etiqueta', 'Conductor', 'Proteccion', 'Corriente Nominal A', etc.) with no semantics. 'Metadatos visuales' loosely gestures at the label/conductor category but gives no meaning for corriente_nominal_a, capacidad_ruptura_ka, dispositivos, or fuente_alterna, which are protection data rather than visual properties.

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 ('Configura') and resource ('metadatos visuales de un alimentador'), and the closing 'sin tocar OpenDSS' pins the scope to visual-only changes. However, it never distinguishes itself from the closely-named siblings configurar_etiqueta_carga_unifilar, configurar_bus_unifilar, and configurar_tipo_carga_unifilar, so the agent must infer which feeder sub-object this targets.

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?

'Sin tocar OpenDSS' implicitly signals when this tool is appropriate versus model-mutating siblings, which is a useful hint. But there is no explicit when-to-use, no named alternative, and no prerequisite guidance for an 8-parameter tool.

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 full behavioral burden. It says what setting is changed but does not disclose side effects, persistence, workspace requirements, or whether the change affects only the diagram or the underlying model.

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 that states the configuration behavior without any filler. It is appropriately concise for the core purpose, even if more detail would be useful elsewhere.

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 three-parameter configuration tool with no annotations, no output schema, and 0% schema description coverage, the description is too thin. It omits parameter meanings, usage context, and behavioral details an agent would need to invoke 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 for three undocumented parameters. It hints at the meaning of the role choice (barra física vs conexión lógica) but does not explain the parameters nombre_bus, etiqueta, or rol, nor any valid values.

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 gives a specific verb (Configura) and resource (bus unifilar) plus the exact setting affected: whether the bus is drawn as a physical bar or logical connection. It is clear enough to distinguish from most siblings, though it does not explicitly name alternative 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?

There is no guidance on when to use this tool versus alternatives such as obtener_configuracion_unifilar or generar_diagrama_unifilar. The context is implied but no when/when-not conditions or prerequisites are stated.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses one behavioral trait — it does not rename the OpenDSS element — but omits permissions, reversibility, persistence, or side effects. Insufficient for a mutation-style configuration 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 verb 'Define'. No wasted words, though its brevity contributes to 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 simple configuration tool with no annotations and no output schema, the description should explain parameter expectations and relationship to sibling tools. It covers only the non-renaming side effect, leaving key context 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 never mentions 'nombre_carga' or 'etiqueta'. Parameter names are self-descriptive in Spanish, but the description adds no semantic detail such as expected format or whether 'etiqueta' is an arbitrary display string.

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 the verb 'Define' and the resource 'rótulo de ingeniería', and clarifies it does not rename the OpenDSS element. It distinguishes from a rename operation but does not name specific siblings or explicitly scope to the load element, which is only implied by the tool 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 indication of when to use this instead of configurar_tipo_carga_unifilar, configurar_bus_unifilar, or other unifilar configuration tools. The non-renaming clause hints at a boundary but is not framed as usage guidance or tied to a condition.

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 does add one genuine behavioral fact: the change does not invalidate the electrical solution, implying no re-solve is required. But it omits whether the change persists, whether it needs a valid load to exist, and what constraints apply to the visual type.

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 filler or repetition. It is efficient, though its brevity borders on under-specification given the tool's requirements.

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 annotations, no output schema, and 0% parameter coverage in a schema listing dozens of unifilar-related siblings, the description is too thin. An agent still cannot determine accepted tipo_visual values or the expected effect on the model.

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 two required parameters, so the description must compensate and does not. 'símbolo' loosely hints at tipo_visual and 'carga' at nombre_carga, but no valid visual types, formats, or naming conventions are given.

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 verb 'Cambia' and resource 'símbolo de una carga' give a concrete action, so the agent knows the tool alters a load's visual representation on the unifilar. However it does not distinguish itself from close siblings such as configurar_etiqueta_carga_unifilar or configurar_bus_unifilar, leaving the boundary fuzzy.

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 statement of when to use this versus the many sibling configurar_* tools, and no prerequisites or conditions given. The only hint is the implicit 'carga' scope, which the agent must infer from the name.

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

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

No annotations exist, so the description carries the full burden. It explains the architectural role (workspace is a view, ChatGPT is the interface, OpenDSS the engine) but omits concrete behavior: that it writes/overwrites an HTML file at ruta_salida, what persistence means, and whether the operation is idempotent or has side effects.

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 first sentence is well front-loaded and states the action. The following two-sentence paragraph is architectural framing whose return on invocation value is questionable, making the overall entry longer than the actionable content warrants.

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 no-annotation tool with an undocumented three-parameter schema and no output schema, the definition leaves key gaps: what 'configurar' actually changes, the file-write side effect, and when to call it instead of sibling workspace tools. The conceptual framing does not 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?

Schema description coverage is 0% across 3 parameters. The description mentions none of titulo, ruta_salida, or auto_regenerar and gives no defaults or format guidance. The Spanish parameter names are somewhat self-evident, but the description adds no meaning 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?

States a specific verb and resource: 'Configura el visor HTML persistente del circuito activo.' An agent can tell it concerns the HTML workspace view rather than the electrical model. However, it never distinguishes itself from close siblings like regenerar_workspace or obtener_estado_workspace, so the boundary of the action remains fuzzy.

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, prerequisites, or alternatives are given. With siblings regenerar_workspace and obtener_estado_workspace present, the description should say whether this sets up versus refreshes versus inspects the workspace, and it does not.

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?

Tool has no description.

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?

Tool has no description.

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 description.

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 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?

Tool has no description.

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?

Tool has no description.

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?

Because no annotations are present, the description carries the full behavioral burden. It usefully discloses that the tool does not run Solve and does not regenerate workspace files, but it omits mutation side effects, permission requirements, whether it overwrites existing state, and what 'admitido' entails operationally.

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 redundant or filler content. It efficiently communicates the action and two key constraints, though the terseness that makes it concise also contributes to the completeness gap.

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 construction tool requiring a complex nested manifest, with no output schema and no annotations, the description is too sparse. It does not explain what the manifest represents, what the tool returns, or how the constructed 'admitted model' relates to siblings like validar_construccion_rev0 or regenerar_workspace.

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 sole parameter is a required nested object ('manifest') with no documentation in either the schema or the description. The description provides no information about the manifest's expected structure or contents, leaving the parameter semantically opaque.

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 ('Construye') and resource ('modelo admitido'), and adds two scoping constraints ('sin Solve', 'sin regenerar archivos workspace') that distinguish it from solver tools and regenerar_workspace. It is clear enough to identify the operation, though 'modelo admitido' is jargon that could be opaque without 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?

The description gives negative constraints (no Solve, no workspace file regeneration) but does not state when to use this tool versus alternatives such as regenerar_workspace, validar_construccion_rev0, or obtener_contrato_construccion_rev0. Usage is implied by the tool name and constraints, but no explicit routing guidance is provided.

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 does disclose two real behavioral traits: the snapshot stays in memory and a SHA-256 is returned. It says nothing about what inputs must exist beforehand, whether any state is mutated, or whether the operation is repeatable.

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 short sentence with zero filler, front-loaded with the action and ending on the returned artifact. Nothing is wasted.

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 tool with no annotations, no output schema and an undocumented parameter, the description is too thin. It does not define what the canonical snapshot comprises, what the netlist directory is expected to contain, or what the caller does with the hash.

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 single parameter directorio_netlist has 0% schema description coverage and a default of 'temp_export_p7a', yet the description never mentions it or explains what directory should be supplied or what happens if it is omitted. This is a gap the description needed to close.

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 (construye), resource (snapshot canónico), a scope qualifier (en memoria) and the return value (SHA-256), which distinguishes it from siblings like exportar_snapshot_proyecto_p7a and verificar_snapshot_proyecto_p7a. It does not explicitly name those siblings, 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?

There is no statement of when to use this tool versus exportar_snapshot_proyecto_p7a, verificar_snapshot_proyecto_p7a, or reconstruir_snapshot_proyecto_p7b, and no prerequisites or ordering guidance. An agent must infer the role of an in-memory build purely from the name.

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

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

No annotations are provided, so the description must shoulder behavioral disclosure. It notes the historical default behavior of bus_fuente and the expectation for professional flows, which adds useful context about defaults and intended use. However, it says nothing about permissions, whether creation is destructive or reversible, rate limits, or side effects, leaving important behavioral gaps for a creation/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?

Two short sentences, front-loaded with the core action, efficient and free of waste. It could be strengthened with a clause naming the intended stage or alternatives, but the current text is appropriately sized.

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 creation tool with no annotations, four parameters at 0% schema coverage, and an existing output schema, the description covers bus_fuente behavior but leaves the purpose of nombre, kv_base, and frecuencia implicit and omits side effects or prerequisite workspace state. An output schema reduces the need to explain returns, but the parameter and behavioral gaps remain.

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 schema provides only titles and defaults without semantic meaning. The description adds meaning for bus_fuente (explicit source bus, default 'sourcebus') but says nothing about nombre, kv_base, or frecuencia semantics. It compensates partially but leaves three of four parameters undocumented in prose, matching a baseline 3.

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 ('Crea un circuito nuevo') and highlights the explicit source bus parameterization, which distinguishes it from implicit-default creation paths. However, it does not contrast directly with the many sibling creation tools (agregar_linea, agregar_transformador, etc.), leaving some ambiguity about when to use this versus adding elements to an existing circuit. Clear but not sibling-differentiating at the highest level.

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?

Implies it should be used for creating circuits and mentions that professional flows must declare bus_fuente explicitly, but gives no explicit when/when-not conditions or named alternatives. Usage is inferred rather than spelled out.

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?

Tool has no description.

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?

Tool has no description.

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 description.

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 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?

Tool has no description.

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?

Tool has no description.

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?

Tool has no description.

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?

Tool has no description.

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 description.

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 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?

Tool has no description.

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?

Tool has no description.

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 does disclose one behavioral rule (secondary P3B factors need explicit opt-in), which is mildly useful. But it never says whether this mutates persisted state, what permissions are needed, what defaults get applied, or what happens to existing conditions when called again — a significant gap for a 13-parameter 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 compact sentence with no filler, and the primary action is front-loaded. However, brevity here shades into under-specification given the parameter surface, so it is concise but insufficient rather than genuinely well-structured.

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 complex tool with 13 parameters, no annotations and no output schema gets a single sentence. The opt-in note is the only behavior conveyed; parameter handling, defaults, and interaction with sibling ampacity tools are absent, leaving the definition materially incomplete 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 0% across 13 parameters, so the description must compensate and largely doesn't. It maps loosely to ib_diseno_a/in_proteccion_a and the factores/permitir_* opt-in flags, but leaves referencia_ib, referencia_in, base_normativa, referencia_condiciones_instalacion, confirmar_condiciones_base, usar_corriente_flujo_como_ib and more 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?

The description names specific quantities (Ib/In/Iz) which signals a calculation-condition-definition tool, so the purpose isn't a pure tautology. However, it never states the resource being configured (an element's ampacity conditions) and gives no differentiation from siblings like evaluar_ampacidad or resolver_factor_normativo_ampacidad. An agent must infer scope from the tool name alone.

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 clause 'factores P3B secundarios requieren opt-in explícito' hints that secondary-dataset factors are gated behind explicit flags, which is light behavioral usage guidance. But there is no statement of when to call this vs alternatives (e.g. listar_datasets_numericos_ampacidad, resolver_base_normativa_ampacidad), nor any prerequisites beyond the opt-in hint.

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?

Tool has no description.

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?

Tool has no description.

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 description.

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 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?

Tool has no description.

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?

Tool has no description.

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 zero annotations, the description carries the full behavioral burden. It does disclose one meaningful trait — that it will not derive zero-sequence parameters — which prevents a wrong assumption. But it says nothing about whether it overwrites an existing equivalent network, what defaults apply, or any side effects on the model state.

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?

It is a single front-loaded clause with no wasted words, which is good structure. But for an 8-parameter tool with no annotations and no output schema, this level of brevity reads as under-specification rather than disciplined conciseness.

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 annotations, no output schema, 8 parameters at 0% schema coverage, and no usage guidance leave the agent with substantial unknowns. Half the parameters are undocumented, and there is no indication of the effect of the call on the model or how it relates to the scenario-selection siblings.

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 all 8 parameters lack documentation. The description covers the meaning of four of them (scc_max_mva, scc_min_mva, x_r_max, x_r_min) but leaves kv_ll, fuente_url, escenario_activo, and fuente_referencia entirely unexplained in both schema and description. It partially compensates but falls well short of the coverage 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?

The description names a specific action ("Define") and the concrete quantities being set (Scc3 and X/R, maximum and optionally minimum), which maps clearly onto the tool's parameters. It also implicitly separates itself from the definir_secuencia_cero_* siblings by stating it does not infer zero sequence. The terseness and missing resource name (the "red equivalente" is only in the tool name) keep it short of a 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?

"no infiere secuencia cero" implies the agent should use the definir_secuencia_cero_* tools for zero-sequence data, which is a useful exclusion. However, it never states when to call this tool versus those siblings, whether it requires prior scenario setup, or what prerequisites exist. Usage is only implied.

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. It does disclose one meaningful behavioral fact: the values are taken as explicit inputs and Z0 is not derived from Scc3, which affects correctness of the zero-sequence study. It says nothing about mutation effects on the scenario/workspace, persistence, or how min/max bounds interact.

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 clause with zero filler; the negative constraint is tacked on with a semicolon and reads efficiently. It is terse to the point of slight under-specification, but nothing is wasted.

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 6-parameter configuration tool with no annotations, no output schema and 0% schema coverage, the description is too thin: it omits which scenario selector applies, what the source URL/reference represent, and how the optional min/max values are interpreted.

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 6 parameters. The description maps only to the R0/X0 concept and leaves the min/max pair semantics, 'fuente_url' and 'fuente_referencia' entirely unexplained; an agent cannot tell what the source URL/reference are for or how the optional bounds are used.

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 and resource: 'Define R0/X0 explícitos de la red aguas arriba por escenario'. The word 'fuente' plus 'aguas arriba' implicitly separates it from the sibling tools definir_secuencia_cero_linea and definir_secuencia_cero_transformador, though no sibling is named explicitly.

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?

'por escenario' implies the context in which the tool applies, and 'no deriva Z0 desde Scc3' tells the agent this is not the path for Scc3-derived zero sequence. However, no alternative is named and no explicit when-to-use/when-not-to-use routing is given.

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 must disclose behavior, but it only states that it applies parameters. It omits whether the operation overwrites existing values, requires permissions or a pre-existing element, and what side effects occur.

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 redundant wording. It is efficient, though its brevity contributes to the gaps noted elsewhere.

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 six-parameter mutation tool with no annotations, no output schema, and zero schema coverage, the description is far too thin. It identifies the core action but omits usage context, many parameter meanings, and behavioral details.

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 description only maps R0, X0, and optional C0 to their corresponding parameters. It says nothing about nombre_elemento, fuente_url, or fuente_referencia, leaving half the inputs 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 ('Aplica') and resource ('Line trifásica'), naming the zero-sequence parameters R0/X0 and optional C0. The reference to 'Line' implicitly distinguishes it from sibling tools for sources and transformers (definir_secuencia_cero_fuente/transformador).

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 no indication of when to use this tool versus alternatives, prerequisites (e.g., the line must already exist), or conditions under which zero-sequence data should be set. The description is purely declarative.

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. It discloses a valuable behavioral constraint—no silent Z0=Z1 assumption and no silent projection to OpenDSS—which is more than many mutation tools provide. But it omits mutation side effects (e.g., what workspace state is changed), required permissions, behavior when data is missing, and any return characteristics. The single behavioral guarantee is useful but incomplete.

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 that wastes no words. It efficiently conveys the core action and a critical behavioral caveat. Every part of the sentence 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?

For a tool with 12 parameters, no annotations, no output schema, and 0% schema description coverage, the description is far too sparse. It lacks parameter semantics, explicit usage guidelines, and most behavioral details an agent needs to invoke the tool correctly. It provides only a high-level purpose and one constraint.

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 12 parameters, and the description adds no parameter-level meaning. It does not explain what uk0_percent, ur0_percent, leakage_share_hv, magnetizing_z0_ratio_percent, or any other parameter represents or how they interact. The description fails to compensate for the complete lack of schema documentation.

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 names a specific verb ('Registra') and resource ('datos Z0 de transformador'), and the added clause 'sin asumir Z0=Z1 ni proyectarlos silenciosamente a OpenDSS' distinguishes it from sibling tools like definir_secuencia_cero_fuente and definir_secuencia_cero_linea. An agent can tell this is the transformer zero-sequence registration tool without opening the schema.

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 when to use it: when you have actual Z0 data and want to avoid assumptions or silent projection to OpenDSS. However, it does not explicitly state when to prefer this over alternatives such as obtener_secuencia_cero or the other definir_secuencia_cero_* tools, nor does it list prerequisites or exclusions. Usage is only implied.

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 behavioral burden, and it only supplies the word 'aislados' (isolated), hinting at sandboxing without explaining what that isolation means. It does not state whether the run mutates the workspace, writes artifacts, requires a prepared circuit, or has limits on concurrency or duration.

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?

It is one short sentence, but the brevity comes from under-specification rather than economy — the sentence omits the resource being studied and the mechanism, so nothing is front-loaded for the agent to act on.

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, no annotations, and one opaque nested parameter leave every question unanswered: what inputs the manifest needs, what the tool returns, and how it relates to the validation/dossier siblings in the motor-start family. The definition is not sufficient to call this 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 coverage is 0% for the single required 'manifest' parameter, which is an open nested object (additionalProperties: true) with no documented fields. The description adds nothing about what the manifest must contain, so an agent cannot construct a valid call from either the schema or the 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 says it runs 'explicit static studies in isolated OpenDSS contexts', but the tool is named ejecutar_arranque_motores (motor starting), and the two do not line up — motor starting is not a 'static study'. It also fails to distinguish this tool from siblings like ejecutar_perfiles_arranque_motores and ejecutar_secuencias_arranque_motores, which are described by name in a nearly identical space.

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, when-not-to-use, prerequisite, or alternative guidance. With several sibling tools covering motor-start profiles and sequences, the agent has no textual basis for choosing this one over them.

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 does disclose a meaningful side effect: FaultStudy switches the OpenDSS solution mode, the fault result is retained as a study, and the viewer is restored to normal power flow to avoid mixing voltages. That is useful state-change context, but it omits permissions, failure behavior, and any notes on the input it requires.

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 action is front-loaded in the first clause ("Calcula Isc y restaura después una solución de flujo"), followed by a compact rationale for the restore behavior. No sentence is wasted, though the two-sentence explanation of the mode switch is slightly more verbose than strictly needed.

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 study-execution tool with no annotations, no output schema, and 0% parameter coverage, the description should carry more. It explains the post-execution state handling well but leaves the required bus argument and the nature of the returned fault result entirely unexplained.

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 required parameter bus_falla, and the description never explains what that bus is, its expected format, or how it is resolved within the workspace. The description therefore does not 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?

The description states a verb and resource ("Calcula Isc ... para el workspace"), so the basic action is identifiable. However, the sibling set contains four explicit variants (ejecutar_cortocircuito_iec60909_3ph, _2ph, _1ph_ground, _2ph_ground), and the description never says which fault type or standard this generic entry point covers. An agent cannot tell it apart from those siblings, so the purpose is vague in 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?

There is no when-to-use or when-not-to-use guidance, and the alternative short-circuit tools in the sibling list are not mentioned. The text describes what happens after execution but never states the condition that should select this tool over the IEC 60909 variants.

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 so well: no automatic dispatch, no cross-check, Sk''/ip/Ith are not derived or promoted for 1F-T in P4C11C, and professional emission stays disabled. These are non-obvious constraints an agent could not guess. It stops short of describing failure modes or result delivery, so not a 5.

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 action, then a tight block of constraints; no filler sentences. Slightly dense but every line 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?

For a zero-sequence-dependent IEC 60909 study tool with no annotations or output schema, the description supplies the critical preconditions and explicitly lists what is NOT computed. The main gap is undocumented parameters, which prevents a 5.

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% with 3 parameters, so the description must compensate. It explains line_endtemp_degree_c's role (required for MIN, per line) but says nothing about bus_falla or lv_tol_percent, and gives no format/units hints. Partial compensation only.

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?

Names a specific verb+resource ('Ejecuta IEC 60909 1F-T MAX/MIN con Z0 explícita') and adds a concrete side effect ('registra V4'). The '1F-T' qualifier cleanly separates it from the parallel siblings ejecutar_cortocircuito_iec60909_3ph, _2ph and _2ph_ground without needing to open any schema.

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?

States prerequisites clearly: zero-sequence of source, lines and transformers must be declared and projectable, and MIN requires explicit 'endtemp_degree' per line. It also rules out automatic dispatch and cross-check. It does not, however, explicitly point to the definir_secuencia_cero_* siblings as the setup step, leaving that inference to the agent.

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 so well: it discloses the experimental pandapower backend, the scoping of the Z2=Z1 assumption (only for the passive symmetric network currently supported, explicitly not universal), the MIN prerequisites, and that output is recorded in V5/V4 with no professional emission. Missing only error/failure behavior and return semantics.

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?

Compact and front-loaded with the fault type first, but it relies on undocumented internal codes (P4C06, V5/V4) and dense jargon that an agent cannot resolve from the definition alone, costing some clarity per sentence.

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 an execution tool with no annotations, no output schema, 6 parameters at 0% schema coverage, the description covers constraints and side effects reasonably but omits error conditions, return shape, and precise per-parameter meaning. Adequate but with clear gaps.

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 6 parameters, so the description must compensate. It references the key parameters conceptually (endtemp_degree by name, ip/Ith via calcular_ip_ith, κ-method, topology/time gates) and bus_falla is required, but it does not clarify defaults, formats, or the tk_s parameter, leaving roughly half the semantics to inference.

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 (ejecuta) and a precise resource (IEC 60909 fase-fase sin tierra / 2F MAX/MIN), and the fault type cleanly separates it from the 3ph, 1ph_ground and 2ph_ground siblings. An agent can route to it without opening the schema.

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 conditional guidance for the MIN mode (requires explicit endtemp_degree per line) and notes the topology/time/κ-method gates still apply, but never states when to choose this tool over the 3ph / 1ph_ground / 2ph_ground alternatives. Usage is implied by fault type rather than explicitly framed.

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, so the description carries the full burden. It does disclose real behavioral detail: pandapower is used only for Z1/Z0, the fault is solved by the audited MCP symmetrical-components solver, ikss_ka is internal-use and ikss_contractual stays False. However it does not clarify side effects of 'registra V4' (persistence/state mutation) or any preconditions, leaving key behavioral aspects opaque.

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?

Reasonably sized at two sentences, but front-loads opaque internal jargon ('extensión operacional 2F-T MAX/MIN', 'registra V4') that conveys little to a new caller, and the useful method/output detail is buried in the second half.

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?

An execution tool with no annotations, no output schema, and three completely undocumented parameters. The description touches on output meaning (ikss_ka, ikss_contractual) and the solver, but omits parameter guidance, preconditions, and the effect of 'registra V4', leaving it under-complete for the tool's 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% and the description never mentions bus_falla, lv_tol_percent, or line_endtemp_degree_c. Zero semantic guidance is added for any of the three inputs, so the description does not compensate for the empty 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?

States a specific verb (Ejecuta) and resource (2F-T two-phase-to-ground IEC 60909 short circuit) and describes the underlying method (symmetrical components solver for the b-c-ground fault). It implicitly distinguishes itself from the 3ph/2ph/1ph_ground siblings via '2F-T' but never names them, so an agent must infer the variant.

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 statement of when to choose this variant over ejecutar_cortocircuito_iec60909_3ph, _2ph, _1ph_ground, or plain ejecutar_cortocircuito. The context is only implied by the fault type in the name; no prerequisites or exclusions are given.

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 discloses meaningful behavior: no automatic dispatch, no cross-check, MIN scenario requires explicit endtemp_degree per line, ip/Ith calculation depends on declared topology, clearing time, and kappa method, registration in V5/V4, and professional_emission remains false. It still omits side effects, error handling, and whether it mutates the workspace beyond registration.

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 purpose is front-loaded in the first sentence, followed by relevant constraints in three compact sentences. There is little wasted text, though some domain jargon is used without unpacking.

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 complex six-parameter analysis tool with no annotations and no output schema, the description covers purpose and several behavioral constraints well. However, it does not describe the return values or result structure, which is a notable gap when no output schema exists, and it provides no explicit routing to alternative short-circuit tools.

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 adds concrete meaning for several parameters by linking endtemp_degree to line_endtemp_degree_c in MIN scenarios, and tying ip/Ith calculation to topology, tk_s (tiempo de despeje), and kappa_method. It does not explain bus_falla or fully define parameter formats, but it substantially improves on 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?

States a specific verb (Ejecuta), standard (IEC 60909), fault type (3F), and operating modes (MAX/MIN) with pandapower experimental. This clearly distinguishes it from sibling tools such as ejecutar_cortocircuito_iec60909_2ph and 1ph_ground.

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?

Implies usage through 'explícitamente' and the note that there is no automatic dispatch or cross-check, which tells the agent when not to expect those behaviors. However, it never explicitly names an alternative tool or states the precise conditions under which this tool should be chosen over sibling short-circuit 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?

With no annotations, the description carries full behavioral burden. It states execution is limited to declared maneuvers/states, but omits side effects, required permissions, reversibility, error behavior, and return format, leaving substantial gaps for a mutation-like tool.

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

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

The single sentence is front-loaded and free of filler, so it is concise. However, it is too terse for a tool with two required nested-object parameters and no annotations, leaving critical gaps rather than achieving appropriate brevity.

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 two required nested objects, no annotations, and no output schema, the description is severely incomplete. It does not explain the manifest, expected input shape, execution outcomes, or side effects, so an agent cannot safely invoke it.

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 only obliquely references 'paquete P12' (likely paquete_escenarios) and never mentions the required 'manifest' parameter, providing no structural or semantic detail for either nested object.

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

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

States a specific action (Ejecuta) and scope (únicamente las maniobras/estados declarados en el paquete P12), giving a clear verb and resource. It does not explicitly differentiate from siblings like validar_escenarios_operativos or generar_dossier_escenarios_operativos, but the scope limitation 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 tool versus validar_escenarios_operativos, generar_dossier_escenarios_operativos, or other ejecutar_* siblings. Only implies it runs the declared scenarios, with no when-not or alternative conditions.

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 this description carries the full behavioral burden. It discloses key side-effect constraints (does not modify the base workspace solution) and failure behavior (returns rejection with compatibility codes for unsupported elements), though it does not cover idempotency or auth/rate limits.

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 short sentences are front-loaded: purpose/scope first, constraints second, failure behavior last. Every sentence adds information and there is no 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?

For a parameterless execution tool with no output schema, the description covers scope, exclusions, and failure behavior well enough. It could be richer about prerequisites or the successful result, but no output schema exists to require that.

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 has no parameters, so there are no parameter semantics to document. Per the rubric, a zero-parameter schema sets the baseline at 4.

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

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

States a specific action (resolve with pandapower) and scopes it to experimental v1, so the engine and mode are clear. It does not distinguish this from sibling flow tools such as ejecutar_flujo_potencia; it only mentions a non-sibling alternative (OpenDSS).

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 context (experimental v1, explicit pandapower) and several when-not constraints: no OpenDSS comparison, no automatic motor selection, no modification of the workspace base solution. It does not name the sibling tool to use instead when those constraints do not apply.

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 implies a compute-plus-write behavior ('actualiza la vista detallada') but never states prerequisites (a configured circuito/workspace), whether results are cached or overwritten, or whether the underlying state is mutated destructively.

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 compact sentence with no filler and the computation front-loaded ahead of the side effect. It is efficient, though the second clause is under-specified rather than merely brief.

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 heavy simulation tool with no output schema and no annotations, the description says almost nothing about what the run produces, how the agent retrieves results, or what 'vista detallada' means. An agent could invoke it but would not know what to expect or do next.

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 is nothing for the description to disambiguate; the baseline of 4 applies. No parameter-level detail is missing.

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 ('Resuelve flujo') plus the engine used ('con OpenDSS'), which distinguishes it from the sibling ejecutar_flujo_pandapower. The trailing clause 'actualiza la vista detallada' hints at a side effect but is vague about what view is updated.

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 statement of when to pick this over ejecutar_flujo_pandapower or analizar_flujo_operacion. The engine name is the only implicit differentiator, leaving the agent to infer the selection condition.

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 behavioral burden. It conveys a scope boundary ('únicamente los puntos explícitos') but omits side effects, required permissions, mutation semantics, and return 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?

A single short sentence with no filler, so it is concise and front-loaded. However, it is under-specified for a tool with two nested object parameters, making the brevity a liability rather than efficient structure.

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 annotations, no output schema, and 0% parameter description coverage, the description is insufficient for an agent to invoke the tool correctly. It does not explain the required nested inputs, what P13C profiles are, or what the tool returns.

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?

There are two required object parameters with 0% schema description coverage, and the description does not mention either 'manifest' or 'paquete_perfiles'. No meaning is added beyond the bare property names.

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 verb (Resuelve) and a scope (puntos explícitos de los perfiles P13C), which is more than a tautology. However, 'P13C' is unexplained jargon and the description does not differentiate this tool from closely named siblings such as validar_perfiles_arranque_motores or ejecutar_secuencias_arranque_motores.

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 explicit when-to-use guidance or alternatives are given. The word 'únicamente' hints at a limitation (only explicit points), but there is no instruction on when this tool should be selected over siblings.

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 supplied, so the description carries the full behavioral burden. It hints at isolated execution contexts, but does not state side effects, whether state is mutated, required permissions, return behavior, or safety profile for an execution tool.

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

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

The single sentence is front-loaded and contains no filler, but it is too terse for a tool with three complex required objects. The structure is clean yet insufficiently developed to guide invocation.

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 tool with three required object parameters, no annotations, no output schema, and 0% schema description coverage, the description is severely incomplete. It does not explain what the packages contain, what sequences are executed, or what the isolated contexts mean 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?

There are three required nested object parameters (manifest, paquete_perfiles, paquete_secuencias) with 0% schema description coverage, and the description does not mention or clarify any of them. The description therefore fails to compensate for the complete lack of parameter documentation.

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 has a clear verb ('Ejecuta') and a nominal resource ('secuencias estáticas declaradas en contextos aislados'), but the purpose remains vague in domain terms and gives no differentiation from siblings such as ejecutar_perfiles_arranque_motores or validar_secuencias_arranque_motores.

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 guidance, prerequisites, or comparison to alternative tools is provided. The agent receives no signal about when this execution tool is preferred over validation or profile-execution siblings.

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 of disclosure. It says the estimation is educational and uses the Lee method, but omits assumptions, limitations, safety caveats, required input conventions, and whether the result is screening-level or detailed. This leaves significant behavioral gaps for a computational tool.

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

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

The description is a single front-loaded sentence with no filler. It is efficiently compact, though its extreme brevity contributes to the missing context rather than being a model of concise completeness.

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 calculation tool with no annotations, no output schema, and no schema descriptions, the description is far too thin. It names the method and educational scope, but an agent still lacks enough context to select and invoke the tool reliably.

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 never mentions any of the four parameters. Although parameter names hint at units such as kV, kA, and mm, the definition adds no parameter meaning beyond the bare schema, leaving the agent to infer how each input is used in the Lee method.

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 and resource: estimating incident energy, and names the Lee method. This distinguishes it from generic arc flash tools, but it does not explicitly differentiate itself from the sibling tool calcular_arc_flash or other arc flash methods.

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 word 'educativa' implies an educational rather than design-grade use case, but there is no explicit guidance on when to use this tool versus calcular_arc_flash or other alternatives. No prerequisites, exclusions, or scenario context are provided.

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 does disclose a meaningful behavioral trait: the operation only reviews presence/traceability and deliberately does not build or compute the model, implying a non-mutating check. It stops short of stating permissions, expected output, or what 'trazabilidad' concretely verifies.

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 short sentence with the exclusion constraint front-loaded; no filler or repetition. It is lean to the point of underspecification, but nothing is wasted.

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 tool whose only input is an opaque nested manifest and which has no output schema and no annotations, the description leaves too much unknown: what 'entradas' means, what traceability is checked, and what result indicates admission. Adequate for a trivial tool, insufficient here.

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?

There is one parameter, 'manifest', a nested object with additionalProperties=true and 0% schema description coverage. The description says nothing about what the manifest must contain or what fields are inspected, so it fails to compensate for the coverage gap on a non-trivial structured parameter.

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 names a verb ('Revisa') and an object ('presencia/trazabilidad de entradas'), which is more than a tautology and clarifies the tool does not build or calculate the model. However, it does not tie itself to the 'pilot real' / P8F context that several siblings (obtener_contrato_p8f1_piloto_real, generar_dossier_piloto_real) share, so distinguishing it from them requires inference.

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 clause 'sin construir ni calcular el modelo' implies a when-not boundary (this is an inspection step, not a construction step), which is useful. But it names no sibling alternative and gives no explicit condition under which an agent should pick this over the contract/dossier tools nearby.

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?

Tool has no description.

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?

Tool has no description.

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 description.

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 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?

Tool has no description.

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?

Tool has no description.

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 behavioral burden. It discloses one useful trait — that it compares without substituting ratings — but does not state whether the operation is read-only, whether it mutates or persists data, or what side effects it may have.

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. It is appropriately sized for its content, though the content itself is sparse.

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 six-parameter evaluation tool with no output schema and no annotations, the description is far too thin. It does not explain return values, expected behavior on failure, or how the required inputs should be supplied.

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 none of the six parameters are documented. The description vaguely references 'falla' and 'Icu o poder de corte', which partially maps to corriente_falla_ka and device ratings, but leaves tension_operacion_kv, fuente_corriente, escenario, and tipo_falla 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 and resource: comparing the fault current against Icu or breaking capacity. This clearly describes the evaluation action, but it does not explicitly distinguish itself from related P5C/P5A siblings such as evaluar_soportabilidad_termica_conductor_p5c or obtener_referencias_proteccion_p5c.

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 explicit when-to-use guidance or alternatives. The only implicit constraint is 'sin sustituir ratings', which notes a limitation but does not tell an agent when this tool is appropriate versus other evaluation 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?

No annotations and no output schema, so the description carries the full burden. It doesn't say whether this is read-only, what checks are performed, what constitutes a pass/fail, or what the result contains. 'Coherencia del modelo activo' is vague about the actual behavioral semantics.

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. Brevity is fine, though it is achieved partly at the cost of necessary 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?

For a validation tool with no parameters, no annotations, and no output schema, the description should clarify what is validated and what the outcome means. Instead it leaves 'P2 contract' and 'active model coherence' undefined, so an agent cannot confidently decide to call it or interpret its 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?

The tool takes zero parameters, so there is no parameter semantics to document; the baseline of 4 applies. The description neither helps nor hurts here.

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 (Evalúa) and two objects (el contrato de producto P2 v1, la coherencia del modelo activo), so the general action is discernible. However, 'P2' is unexplained jargon and the description does nothing to distinguish it from sibling evaluators like evaluar_cierre_p3, evaluar_cierre_p5, or evaluar_cierre_p7d_engineering_preview.

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 invoke this tool versus the many other 'evaluar_*' siblings, nor any prerequisites (e.g. that a P2 contract must exist). The agent must infer usage entirely from the name.

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

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

With no annotations, the description carries the full behavioral burden. It discloses the key blocking behavior ('debe bloquear avance mientras falte evidencia/cobertura normativa'), but does not clarify whether the tool only evaluates or also mutates state, what it returns, or any permission 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 well-formed sentence front-loads the action and then states the current expected outcome. There is no redundant or filler text.

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

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

Given zero parameters, no annotations, and no output schema, the description should carry the full burden of explaining the evaluation result and what happens on success or failure. It states the blocking condition but omits return format, side effects, and how the outcome should be interpreted, leaving an agent under-informed for a gate 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 tool takes zero parameters, so there are no parameter semantics to document. The baseline score of 4 applies because the schema coverage is trivially complete and the description need not add parameter-level detail.

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 ('Evalúa') and resource ('gate formal P3'), making the core action clear. It does not explain what P3 covers or explicitly contrast with sibling gates like evaluar_cierre_p2 or evaluar_cierre_p5, leaving differentiation implicit through the gate number.

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 gives a contextual condition — the gate should block progress while normative evidence/coverage is missing — which implies when the tool matters. However, it does not say when to call this tool versus the other gate evaluators or preparation tools, nor does it state prerequisites or exclusions.

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 behavioral burden, yet it only says the tool evaluates readiness. It does not disclose what 'limitaciones' means, whether the check is read-only or mutates state, what authorization is required, or what determines a pass/fail.

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 filler, which is structurally clean. It is terse to the point of under-specification, but it wastes no 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 no output schema and no annotations, the description is the only source of context, and it leaves the agent unable to know what the evaluation returns or what 'ready with limitations' implies. For a phase-gate tool in a complex domain, this is too thin.

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 the schema-based baseline is 4. There is nothing for the description to clarify beyond what the empty schema already conveys.

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 ('Evalúa') and a specific gate resource (whether P5-v1 is ready with limitations to deliver to P7), so the agent knows it's a phase-closure check rather than a data-getter. It distinguishes itself from sibling getters/builders by naming the P5→P7 handoff, though it doesn't explicitly contrast with evaluar_preparacion_proteccion_p5a or evaluar_cierre_p2/p3.

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 when-to-use or when-not-to-use guidance, and no named alternative despite a whole family of sibling 'evaluar_cierre_*' and 'evaluar_preparacion_*' gate tools. Usage is only inferred from the phase naming in the single sentence.

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 behavioral burden. It adds one meaningful constraint ('without enabling professional emission'), implying a safe/preview evaluation, but says nothing about required prior state, whether it mutates anything, or what the result signifies.

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 filler or repetition. It is efficient, though its brevity edges toward under-specification rather than true economy.

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 gate-evaluation tool with no annotations and no output schema, the description should convey what the gate checks and what a pass/fail implies. The one-line summary leaves the agent unable to predict the outcome or the conditions that must hold before calling it.

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 is nothing for the schema to document and no syntax for the description to add. Baseline 4 applies for a parameterless tool.

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 verb ('Evalúa') and a resource ('gate de MCP Eléctrico 0.9'), but 'gate' is vague and the description never says what is being verified or closed out. Against many sibling 'evaluar_cierre_pX' tools it does not explain how p7d differs from p2, p3, or p5.

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 invoke this versus the other gate/closure evaluators or the many 'evaluar_*' siblings. The only contextual clue is 'sin habilitar emisión profesional,' which hints at a preview mode but is not framed as usage 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?

With no annotations, the description carries the full burden, and it does disclose two meaningful boundaries: it does not execute engineering and does not enable professional emission. It still omits whether the operation is read-only, what it mutates or persists, and what a gate result means, so the safety profile is only partially clear.

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 well-formed sentence with the scope qualifier front-loaded. It is appropriately sized, though the terseness is partly a symptom of under-specification rather than genuine economy.

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 gate-evaluation tool with no output schema and no annotations, the description should convey what the evaluation produces (pass/fail, which gate criteria, next step). Instead it supplies only one sentence of scope, leaving the agent unable to interpret or 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?

The tool takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. Schema coverage is 100% trivially since the property set is empty.

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 verb 'Evalúa' and a scoped resource 'el gate final P8', plus a boundary ('sin ejecutar ingeniería ni habilitar emisión profesional') that distinguishes it from execution siblings. However, the P8/P8F5 jargon is never unpacked, so an agent cannot tell what is actually being evaluated or how it differs from the many sibling evaluar_cierre_* gates.

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 guidance, no prerequisites, and no named alternatives among the numerous sibling gate evaluators (p2, p3, p5, p7d). The only usage signal is negative scope ('sin ejecutar ingeniería'), which is implied rather than stated as a selection rule.

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 behavioral burden. It discloses only a narrow scope exclusion and says nothing about whether the evaluation is read-only, what inputs are required, what result is produced, or how failures are reported.

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 short sentence, but it is drastically under-specified rather than concise. It omits information an agent needs while adding only a small scope caveat.

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 seven required parameters, no annotations, no output schema, and no schema descriptions, the description is far too thin to support correct invocation. It provides almost no context beyond the tool name.

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?

All seven parameters are required and schema description coverage is 0%, yet the description mentions none of them. It does not compensate for the empty schema documentation in any way.

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?

It states a verb and a scope ('Evalúa margen temporal puntual') and adds a negative scope clause ('no declara selectividad total/backup'), which gives some differentiation. However, 'margen temporal puntual' remains vague and the description does not clearly distinguish this tool from sibling coordination and contract 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 phrase 'no declara selectividad total/backup' implies a limitation on when it applies, but there is no positive when-to-use guidance, no prerequisites, and no alternate sibling named. An agent cannot confidently choose this tool versus related P5e contract or selectivity 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?

No annotations and no output schema, so the description carries the full behavioral burden, yet it only adds the cryptic phrase 'solo dentro del dominio publicado'. It does not disclose whether the tool is read-only, what it returns, what 'dominio publicado' means, or any side effects.

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?

It is a single short sentence, but it is under-specified rather than concise — no wasted words because there is almost no content at all. Front-loading is irrelevant given the length.

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 annotations, no output schema, two undocumented parameters, and a one-clause description, the definition is far too thin for an evaluation tool whose inputs (device and current) and result are entirely opaque.

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?

Two required parameters (dispositivo, current_a) exist with 0% schema description coverage, and the description mentions neither. There is nothing to tell the agent what 'dispositivo' expects or what units/range 'current_a' uses.

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 ('Evalúa') and resource ('la curva vinculada'), so an agent knows it evaluates a previously linked curve. However, it does not clarify what the evaluation produces or how it differs from the sibling 'evaluar_dataset_tcc_p5b', leaving the purpose only vaguely bounded.

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 context, no prerequisite (e.g., that a curve must be linked first), and never names an alternative among the many curve/dataset siblings. Usage must be inferred 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?

Tool has no description.

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?

Tool has no description.

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 description.

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 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?

Tool has no description.

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?

Tool has no description.

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 exist, so the description carries the full burden. It does disclose one meaningful behavioral trait — that it does not mutate READY_DATA or advance P3 maturity — which tells the agent this is a non-destructive classification. However, it says nothing about what it reads, whether it requires existing factor records, or what happens on missing data.

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 short clause with no filler, and the non-mutation constraint is included rather than padded. Nothing wasted for a tool of this scope.

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 zero-argument tool with no output schema, the description must explain what state it operates on and what it produces. It says only that it classifies 'evidencia de factores' without naming the source of that evidence or the resulting classification, and the intent-vs-name inconsistency leaves real ambiguity about what the agent will get back.

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 the baseline is 4. Nothing in the description needs to compensate for undocumented inputs, and the absence of arguments is consistent with an operation that acts on existing workspace state.

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