https://fachrechner.com/api/v1/mcp

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

Annotations already declare readOnlyHint, idempotentHint and a closed-world tool; the description adds value beyond that by stating the computed outputs (current I [A] and power P [W]), which matters because there is no output schema. It omits any note on the meaning or effect of the region parameter on the result.

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 plus a short result line; the formulas and outputs are front-loaded with no filler. Minor redundancy between 'Ohmsches Gesetz Rechner online' and 'berechnen' keeps it from a 5.

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

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

With no output schema, the description correctly fills that gap by naming the returned values and their units. For a simple three-parameter pure calculator that is nearly sufficient; only the role of the region parameter is left 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 100%, so the baseline is 3, but the description goes further by defining the mathematical relationship between the voltage and resistance inputs and the derived outputs. The one gap is that the region enum (DE/CH) is never mentioned or explained in connection with the calculation.

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 the specific operation (Ohm's law calculation) and the exact formulas applied (I = U / R, P = U · I), and states the returned quantities. It is clear but does not distinguish itself from any sibling; the sibling names (bot_010 etc.) are opaque, so no differentiation is possible or offered.

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

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

Usage is implied by 'Rechner online berechnen' — call this when you need current and power from voltage and resistance. There is no explicit when-to-use/when-not-to-use guidance and no named alternative for related electrical calculations.

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

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

Annotations already declare readOnlyHint, idempotentHint, and closed-world behavior, so the safety profile is covered. The description adds useful behavioral context through the calculation rule and the exact set of returned values, including units and the special case 0 = over 125 A.

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 front-loads the purpose and selection rule, then lists the result values without filler. It is dense and somewhat run-on, but the enumerations are relevant and earn their 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?

There is no output schema, so the description appropriately supplies the returned result fields and their units. Combined with the fully documented input schema and safety annotations, an agent has enough context to invoke this read-only calculator 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 100%, so all four inputs (region, cos φ, leistung_watt, spannung_volt) are fully documented in the schema. The description discusses domain quantities but does not add input-parameter meaning beyond what the schema already provides, so the baseline 3 applies.

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 calculation/selection task for Leitungsschutzschalter using the rule I_B ≤ I_n ≤ I_z, and enumerates the resulting values. The verb and resource are clear, though the opaque sibling names provide no basis for explicit differentiation.

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 the tool is for selecting a circuit breaker by formula, but gives no explicit when-to-use, when-not-to-use, or alternative guidance. Sibling tools are not mentioned at all.

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

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

Annotations already establish this as a safe, idempotent, closed-world read. The description adds real value beyond that: it names the standards applied, the conversion factor f, and precisely enumerates the four returned quantities including which one is governing ('maßgebend'), compensating for the absent output schema.

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 dense sentence stating purpose and standards, followed by a bullet-style enumeration of the returned values. Front-loaded, zero filler, and the output list is load-bearing given no output schema.

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 fully-defaulted, no-required-parameter calculator, the description covers purpose, standards, installation type and all returned values. Minor gaps remain around the AC configuration (single-phase vs three-phase) implied by the 230 V default, but nothing an agent needs to invoke it correctly is missing.

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

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

Schema description coverage is 100%, so every parameter including the region enum and the f factor semantics is already documented. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 precise verb+resource: computes the minimum copper conductor cross-section from voltage drop and current-carrying capacity, citing the governing standards and installation type B2. The scope is unambiguous, but with sibling names being opaque IDs it offers no differentiation from the other bot_* calculators.

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 scope constraints (copper only, Verlegeart B2, DE/CH regime via the region parameter) imply when the tool applies, but there is no explicit statement of when to prefer a different tool or what the tool does not cover (e.g. aluminium, other installation types).

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds the result shape (annual kWh yield and € savings), which is genuinely valuable given there is no output schema, but says nothing about calculation assumptions or rounding.

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, front-loaded with the primary action, followed by a qualifier and the return values. Every sentence carries information; 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?

All parameters are optional with defaults and fully documented in the schema, and the missing output schema is compensated by naming the two result values. The only gap is the stray mention of 'Neigung', a factor the caller cannot actually supply.

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

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

Schema description coverage is 100%, so all four parameters are already documented with ranges and defaults. The description only loosely maps to them ('Standort' ≈ region) and introduces 'Neigung' (tilt), which has no corresponding parameter — mildly misleading but not harmful.

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: 'Berechnen Sie den jährlichen Stromertrag Ihres Balkonkraftwerks', refined by 'Einfacher Ertragsrechner für Solarmodule'. An agent can tell this is a photovoltaic yield estimator, though siblings (bot_XXX identifiers) give no basis for explicit differentiation.

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 establishes clear usage context — estimate annual yield and savings for a balcony solar installation, factoring in location and tilt. It offers no explicit exclusions or named alternatives, but the scope is unambiguous enough to route correctly.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds the key behavioral payload absent from annotations: the exact result quantities and their units (kWh/a, kWh/month, kWh/day), which is important since there is no output schema.

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, front-loaded with the conversion, followed by the concrete outputs. No filler; the result list is dense but earns its place given there is no output schema.

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

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

With no output schema, the description takes on returning the result shape and units, which it does thoroughly. A simple read-only calculation tool with fully described parameters is adequately covered; only the usage decision rule is missing.

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

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

Schema description coverage is 100%, so the schema already documents region, heizlast_kw, and volllaststunden with ranges and enum meaning. The description only gestures at 'Heizlast und Volllaststunden' without adding format or constraint detail beyond the schema, matching the 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 and resource: converting heating load (kW) into energy (kWh) over year/month/day periods. The domain is unambiguous. It cannot differentiate from siblings because siblings are opaque bot_XXX identifiers, so sibling-level clarity is not achievable 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?

The description implies usage (calculating annual/monthly/daily energy from Heizlast and full-load hours) and mentions a formula and example, but never says when to pick this tool over alternatives or what preconditions apply. Usage must be inferred.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds the concrete output (U-value in W/(m²·K)), which is useful, but says nothing about defaults applying when no parameters are given or how the region affects the calculation.

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, output stated up front, no filler. Appropriately sized for a simple three-parameter calculator.

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

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

There is no output schema, and the description does state the returned quantity and unit, which is what an agent most needs to know. The absence of any note that all parameters are optional with defaults is a minor residual gap.

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

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

Schema coverage is 100%, so all three parameters are documented in the schema with ranges, defaults and units. The description's 'wenige Eingaben' adds no parameter meaning beyond that, so baseline 3 applies.

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?

Specific verb plus resource: calculate the U-value of one's insulation, with the output unit stated. It is unambiguous on its own, but the sibling names (bot_009, bot_017, …) are opaque, so no differentiation from alternatives is possible or attempted.

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 says nothing about when to use this rather than another tool, nor about prerequisites or limits. 'Mit wenigen Eingaben' hints at a lightweight calculator but gives no routing guidance.

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

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

Annotations already establish that this is a read-only, idempotent, closed-world operation; the description adds the concrete behavioral output (three named quantities with units), which is real information beyond the annotations. It does not mention numerical precision or rounding, which is the only notable gap for a computation 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?

It is short and front-loaded, with the operative computation first and the return values last. Minor waste: 'Einfach und kostenlos' is marketing filler, and the three output quantities are effectively listed twice, though the second listing adds the units.

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

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

With no output schema, the description correctly compensates by spelling out the three returned values and their units, and the input side is fully covered by a 100%-documented schema. The only missing piece is what the region parameter changes in the result, which is left unstated.

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

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

Schema description coverage is 100%, with types, defaults, ranges, and the region enum all documented, so the schema carries the parameter burden and the baseline of 3 applies. The description confirms the input geometry ('aus Tiefe und Neigungswinkel') but adds nothing about the region parameter's role in the calculation.

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 ('Dachneigung für ein Pultdach berechnen') and enumerates exactly what is computed and from which inputs, so an agent immediately knows what the tool does. It cannot differentiate the tool from its siblings, but all siblings are opaque bot_0XX identifiers, so that differentiation is not achievable through this text.

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

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

Usage is implied: an agent can infer it should call this when it needs the pitch, rise, or rafter length of a mono-pitch roof. There is no explicit 'use this instead of X' routing and no statement of prerequisites or exclusions, though for a self-contained calculator there may be no meaningful alternatives.

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

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

Annotations already establish that this is a read-only, idempotent, closed-world calculator, so the description does not need to repeat safety hints. The description adds useful behavioral context by listing the computed outputs, including expected string voltage, maximum string voltage, estimated active module count, and deviation percentage.

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 and the description is compact overall. The long output enumeration is justified because there is no output schema, though the single dense sentence could be slightly easier to scan if split.

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?

All eight inputs are fully described in the schema, and because there is no output schema, the description appropriately explains the computed result fields. It does not cover assumptions or limitations of the calculation, but it is complete enough for an agent to invoke the calculator 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 100%, so every one of the eight parameters is already documented in the schema. The description does not add extra parameter-level semantics beyond what the schema provides, which is acceptable at the baseline for fully covered schemas.

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

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

The description states a specific verb and resource: calculating expected and maximum PV string open-circuit voltage and checking measurement deviation per DIN EN 62446. It is very clear about the calculation domain, but it does not explicitly differentiate itself from the many sibling tools, whose names are opaque identifiers.

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 clear usage context by saying the calculation is for commissioning ('für die Inbetriebnahme'). It does not state when not to use the tool or name any alternative 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so safety and determinism are covered. The description adds that results include thermal and electrical power and that efficiency is selectable, but it omits any formula, default behavior, or explanation of how the region parameter affects results.

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 three short sentences: purpose first, then a note about the extra efficiency-based output, then the result fields. It is front-loaded and contains no filler, though it could be marginally tighter.

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 a simple, fully documented schema and strong safety annotations, the description is nearly complete. It compensates for the missing output schema by listing the two output quantities. It does not explain the region parameter's effect on results, but the schema describes that parameter explicitly.

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

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

Schema description coverage is 100%, and the schema itself documents all four parameters with titles, ranges, defaults, and enum values. The description mentions volume flow and temperature difference, and implicitly the efficiency parameter, but adds no meaning beyond what the schema provides. Baseline 3 is appropriate because the schema does the heavy lifting.

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

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

The description clearly states a specific calculation: heating power in kW from volume flow and temperature difference, plus electrical power at a selectable efficiency. It names the output quantities, so an agent knows exactly what the tool does. Sibling differentiation is not possible because all sibling names are opaque, but the purpose itself 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 guidance on when to use this calculator versus alternatives, no prerequisites, and no exclusions. The description only states what the tool computes, leaving usage decisions entirely 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?

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description goes further by enumerating the three returned figures (net volume, order quantity incl. waste, estimated mass) — genuinely valuable since there is no output schema — but it omits the density assumption behind the mass estimate and the rounding 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?

Three tight sentences: what it computes, what it accounts for, and exactly what comes back. Front-loaded and free of padding, with the output contract placed last where it is most useful.

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 pure calculation tool with no output schema, all five parameters fully documented and no required inputs, the description supplies the missing return-value contract. Only the density assumption for the tonnage estimate and whether defaults are sensible for a typical slab are left unstated.

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

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

Schema description coverage is 100%: every parameter has a title, unit, range and default, and the region enum is fully explained. The description's restatement of 'Länge, Breite und Dicke' and the Verschnittzuschlag adds no syntax or semantics beyond what the schema already provides, so the baseline of 3 applies.

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 (Betonmenge in m³ berechnen) plus the concrete element types it covers (Platten, Bodenplatten, Fundamente) and the exact inputs. The tool is unmistakable in intent, though with only opaque bot_NNN siblings the description can't differentiate it from any alternative.

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

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

Usage is implied by the scope ('für Platten, Bodenplatten und Fundamente'), giving the agent enough to know it fits slab/foundation volume estimation. There is no explicit when-to-use/when-not, no mention of related tools, and no note that all parameters are optional with defaults.

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

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

Annotations already declare readOnlyHint, idempotentHint and closed-world, so safety is covered. The description adds genuinely useful behavior beyond that: it discloses that one bag count is reported unrounded and another as whole sacks, which tells the agent how to interpret the numeric outputs.

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

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

Two sentences, front-loaded with the operation and the inputs, then the outputs. The only mild waste is the opening repetition of the title before the substantive content.

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

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

With no output schema, the description correctly compensates by enumerating the four returned quantities with units and rounding semantics. All six parameters are schema-documented, so nothing an agent needs before calling is missing; only the opaque 'region' effect is left entirely to the schema.

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

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

Schema description coverage is 100%, so units, ranges and the DE/CH enum are already documented in the schema. The description reinforces the concepts (Fläche, Dicke, Verschnitt) but adds no syntax or selection advice beyond what the properties already say; baseline 3 applies.

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?

Specific German verb-plus-resource with an explicit inventory of what is computed (Volumen in m³, Gewicht in kg, Sackanzahl mit Verschnitt), so an agent knows exactly what the tool returns. It cannot distinguish itself from the opaque bot_0xx siblings, but the purpose itself 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?

It states which inputs to supply ('Fläche und Dicke eingeben') but gives no guidance on when to choose this tool over alternatives, nor any prerequisites or exclusions. Usage has to be inferred from the input list alone.

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

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

Annotations already confirm it is a read-only, idempotent, non-open-world calculation. The description adds useful output information (results in both l/min and m³/h) that is not available from annotations or an output schema, though it does not explain rounding or region 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?

Two sentences, front-loaded with the core calculation and followed by the additional output unit. There is no unnecessary text, and the result fields are stated compactly.

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 three-parameter calculator with full schema coverage and annotations, the description is nearly complete. It covers the calculation and both output units; the region parameter is explained by the schema, so no critical gap remains.

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

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

Schema description coverage is 100%, so the schema already documents all three parameters fully, including ranges and defaults. The description mentions the diameter and velocity but adds no parameter meaning beyond what the schema provides; baseline 3 is appropriate.

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

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

The description uses a specific verb and resource: calculating volumetric flow (Volumenstrom) in l/min from pipe inner diameter and flow velocity. It is clear what the tool does, though it cannot meaningfully distinguish itself from the opaque sibling IDs.

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

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

Usage is implied by the calculation context, but there is no explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. The context is clear enough for an agent to infer it is a straightforward calculator.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds return-value context that matters because there is no output schema: it states that the result is the required cross-sectional area and inner diameter, with units. It does not disclose assumptions or limits of the calculation, so a 3 is appropriate.

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

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

Two sentences, front-loaded with the computation and followed by the returned quantities. Nothing redundant and nothing that could be cut without losing 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 small, pure-calculation tool with full schema coverage, the description covers inputs and outputs adequately, which is important since no output schema exists. The one gap is the unexplained region parameter, whose effect (if any) on the computed diameter is left to the agent to guess.

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

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

Schema coverage is 100% – both computational inputs (flow_m3h, velocity_ms) have ranges and units documented in the schema. The description restates those two inputs without adding syntax or formula detail. The third parameter, region (DE/CH standards), is never mentioned in the description, so its relevance to the result is 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?

Names a specific computation (pipe diameter from volumetric flow rate and flow velocity) and even enumerates the two outputs (cross-sectional area in m², inner diameter in mm). This is far more than a restatement of the title. It loses a point only because the sibling tools are opaque identifiers, so no differentiation between tools is possible or attempted.

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

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

Usage is implied rather than stated: an agent can infer this is a sizing/calculation tool from the inputs and outputs. There is no explicit guidance on when to use it, no constraints on when the result is invalid (e.g., turbulent vs. laminar assumptions), and no alternative tools named.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, consistent with a pure calculator, so the bar is lower. The description goes beyond them by enumerating the returned result quantities and disclosing the 2/3 safety factor applied to Zs,max, which is real added context an agent could not infer otherwise.

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

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

Two sentences: the first front-loads purpose and normative basis, the second enumerates outputs with units. No filler, though the output enumeration is slightly list-like rather than integrated prose.

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

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

No output schema exists, so the description correctly compensates by listing the four return values with units, and the input schema fully covers the five parameters. It would be stronger if it stated the computation is side-effect-free and deterministic rather than leaving that to annotations.

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

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

Schema description coverage is 100%, with titles, ranges, defaults and even the LS-type-to-factor mapping documented inline. The description adds nothing about m, u0, i_n, z_s or region, so baseline 3 is appropriate since the schema already carries the full burden.

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 ('Berechnen') and concrete resources (Abschaltstrom, zulässige Schleifenimpedanz, Kurzschlussstrom, Reserve) scoped to DIN VDE 0100-410/600. The purpose is unambiguous, though the opaque tool name 'bot_038' and the undifferentiated sibling list mean no differentiation can be signalled beyond the title.

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 standards reference (DIN VDE 0100-410/600) implies the engineering context in which the tool applies, and 'erforderlichen Abschaltstrom' implies a verification/design scenario. However there is no explicit when-to-use, no when-not-to-use, and no alternative tool named — usage must be inferred.

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

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

Annotations already establish readOnly/idempotent/closed-world, so the safety profile is covered. The description adds value by naming the returned quantities, but it never explains the relationship between them (P_AC = P_DC/k, S_AC = P_AC/cos phi) or what the region switch actually changes, so behavioural insight is partial.

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

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

Two sentences, front-loaded with the computation and followed by the result list; the second 'Ergebnis' clause is slightly redundant but the output enumeration earns its place given there is no output schema.

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, listing P_DC/P_AC/S_AC is necessary and present. However, the region parameter (DE vs CH standards) is never mentioned, nor are any assumptions, rounding, or default behaviour, leaving a real gap for a calculation tool whose outputs feed downstream sizing decisions.

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

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

Schema description coverage is 100% and every property carries a title, range and default, so the schema does the heavy lifting. The description only restates n_module, p_modul, k_dc_ac and cos_phi and omits the region parameter entirely, adding nothing beyond the schema. Baseline 3 applies.

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?

Specific verb and resource: computes inverter power from module count, module power and DC/AC ratio, and names the three returned quantities. It cannot be differentiated from the opaque sibling names (bot_009, bot_040, ...), so it stops 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?

The input-to-output flow implies when the tool applies (sizing an inverter for a given array), but there is no explicit when-to-use/when-not-to-use statement or comparison to any alternative. For a self-contained calculator this is adequate but leaves routing to inference.

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

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

Annotations already declare readOnlyHint, idempotentHint and a closed-world scope, so the safety profile is covered. The description adds real value by enumerating the exact result quantities (ΔU [V], ΔU [%], ΔP [W], minimum cross-section, recommended standard cross-section) and the design rule (ΔU ≤ 1 %, min. 4 mm²) that underlies the output — useful since no output schema 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?

Two sentences, front-loaded with the calculation purpose followed by the result list; no filler. The output enumeration is somewhat list-heavy but earns its place given there is no output schema.

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?

All five parameters are optional with defaults and fully documented in the schema, and the description compensates for the absent output schema by naming every returned value. What remains missing is context on domain assumptions (one-way vs round-trip length, applicability limits) and the absence of sibling routing, which keeps it short of 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 description coverage is 100 % — every parameter carries a title, unit, range and the region enum is explained in the schema itself. The description adds no parameter-level information (e.g. it does not clarify that 'laenge' is one-way length and gets doubled, nor how region changes the standard applied). Baseline 3 applies when the schema does the work.

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 calculation domain: voltage drop, relative voltage drop, power loss and minimum conductor cross-section for a DC solar cable, citing VDE 0100-712. An agent knows exactly what computation this performs. It cannot distinguish from siblings, but the siblings are anonymized bot_XXX names with no semantics to differentiate against, so no penalty beyond the missing comparison.

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

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

Usage is only implied by the subject matter — an agent infers this is for PV string cable sizing, but the description never states when to use it, when another tool is preferable, or any prerequisites (e.g. that lengths are one-way, or that region selects the applicable standard). No exclusions are offered.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, so the safe pure-calculation profile is covered. The description adds real value by enumerating the three concrete results and their units (kg, kN/m², %), which matters because there is no output schema. It stops short of stating assumptions (e.g. which norm governs ballast values), which is the only remaining gap.

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

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

Two sentences: the first gives the computation and the comparison, the second lists results with units. No filler, and the core operation is front-loaded.

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

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

For a six-parameter calculation tool with no output schema and no required inputs, the description is complete enough: it names the outputs and their units so the agent knows what comes back, and all inputs are fully documented in the schema. What is missing is any note on the normative assumptions behind the calculation, which would help interpret edge results.

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

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

Schema description coverage is 100% with titles, units, ranges and defaults for all six parameters, so the schema does the heavy lifting. The description only implicitly touches parameters via 'je Modulfeld' and 'zulässige Lastreserve' and adds no syntax or interpretation 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 (berechnet) and resource (Flächenlast einer ballastierten PV-Anlage auf dem Flachdach je Modulfeld) plus the comparison against the roof's load reserve. The three returned quantities are named with units. It does not differentiate itself from any sibling, but the sibling list is opaque IDs so no differentiation is possible 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?

The description says what is computed but never when to use this tool, when not to, or what alternative exists for related roof/PV calculations. An agent must infer the trigger (ballasted flat-roof PV load check) from the purpose sentence alone.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so safety is covered. The description adds genuine value by enumerating the four computed outputs (s_k, mu_1, q_k, and mass in kg/m²) since no output schema exists. It does not disclose that all parameters have defaults or how the region switch alters the calculation, which keeps it below 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?

Two sentences, front-loaded with the method and inputs, followed by the outputs with units. Nothing is redundant or padded.

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

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

For a five-parameter, all-optional calculation tool with no output schema, the description covers purpose and return values well. The remaining gap is the unaddressed region switch, which determines whether SIA 261 or DIN VDE rules apply and materially changes the result.

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

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

Schema description coverage is 100%, so the schema itself documents all five parameters, making 3 the baseline. The description reinforces four of the five inputs but says nothing about the region parameter — the most confusing one, whose enum mixes a national standard choice (DIN VDE vs NIN/SIA) with unrelated marketplace references — so it does not resolve the ambiguity the schema leaves.

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 computation and standard: characteristic snow load on roofs per SIA 261, derived from reference altitude, roof pitch, and exposure/temperature coefficients. It is far from a restatement of the title. It loses a point because it presents the tool as Switzerland-only while the schema exposes a region parameter defaulting to DE (Germany/Austria, DIN VDE), leaving the actual scope ambiguous.

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 select this tool versus alternatives, no statement of prerequisites, and no note that all five inputs are optional with typical defaults. The only implicit cue is the SIA 261 standard, which an agent must interpret on its own.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and idempotentHint=true, covering the safety profile. The description adds the formula assumption (round solid conductor) and explicitly lists the return values (diameter and radius in mm), which goes beyond the annotations.

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

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

Three sentences with clear front-loading: purpose first, then formula caveat, then output. No redundant or filler text; every sentence contributes.

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

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

For a simple two-parameter calculator with full schema coverage and annotations, the description is complete: it explains what is calculated, under what assumption, and what results to expect. Nothing an agent needs in order to call it correctly is missing.

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

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

Schema description coverage is 100%, and both parameters are fully documented with enums, ranges, and defaults in the schema. The description adds no further parameter meaning beyond what the schema already provides, so the baseline of 3 is appropriate.

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

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

The description states a specific verb and resource: converting cable cross-section (mm²) into conductor diameter, and even names the applicable formula condition (round solid conductor with equal cross-sectional area). The purpose is unmistakable, although sibling tool names are opaque and provide no contrast.

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 or when-not-to-use guidance is given; the calculator context is implied by the description. With no alternative tools named, an agent must infer this is the right tool for cross-section-to-diameter conversion.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds value by enumerating the four returned quantities with their units, which matters because there is no output schema. It does not disclose the underlying formulas or assumptions (e.g. that U defaults to 400 V and results are derived per-phase/three-phase), leaving a small gap.

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

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

Two sentences, front-loaded with the computation and followed by a compact result list with units. The second sentence partly restates the first, but the unit annotations earn their place given no output schema.

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 pure calculation tool with zero required parameters, full schema coverage and read-only annotations, the description supplies what is missing: the exact output quantities and units. Only the calculation assumptions (power factor and efficiency treatment, breaker selection rule) remain undocumented.

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

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

Schema description coverage is 100%, with units, ranges and defaults documented for all five parameters, including the DE/CH region enum. The description adds nothing beyond the schema about parameter meaning or interaction (e.g. how η and cos φ feed the calculation), so the baseline 3 applies.

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 concrete verb and a precise set of computed outputs: Wirkleistung P_auf [kW], Scheinleistung S [kVA], Leiterstrom I [A] and the IEC 60898 breaker rating for a 400 V three-phase system. That is far more specific than the title alone. Sibling differentiation is impossible because the siblings are opaque IDs (bot_009…bot_065), so full marks on that axis cannot be earned.

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 domain (three-phase motor/supply sizing at 400 V) implies when the tool applies, but the description never states when to use it versus alternatives, nor any prerequisites such as needing the shaft output power or efficiency. Usage is left to inference from the title and parameter names.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description usefully states the return value ('Leistung [W]'), but it does not explain how the region parameter affects the calculation or results.

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

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

Two short sentences, with the core operation front-loaded and the output unit stated immediately. The middle marketing phrase ('Schnell, präzise und kostenlos') is the only waste.

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 3-parameter pure calculator with no output schema, the description is nearly sufficient: it states inputs, the operation and the result unit. The only gap is whether the region selection influences the arithmetic or merely the applicable standard.

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

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

Schema description coverage is 100%, so all three parameters, their ranges and the DE/CH enum are fully documented in the schema. The description adds no parameter-level meaning beyond what the schema already provides; baseline 3 applies.

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 concrete verb and resource: computing electrical power in watts from current (amperes) and voltage (volts), and names the output unit. It is specific enough to act on, but gives no differentiation from the many bot_* siblings, which are opaque anyway.

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 what alternative exists; 'Schnell, präzise und kostenlos' is marketing filler rather than usage context. An agent must infer the use case from the title alone.

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

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

Annotations already declare readOnly/idempotent/closed-world, so the safety bar is low. The description adds genuinely useful context by naming the two returned quantities (heat energy during minimum runtime in kWh and minimum buffer volume in liters), which matters because there is no output schema.

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

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

Two sentences, front-loaded with the computation and followed by the result list; no filler or repetition of schema constraints.

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

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

For a read-only pure calculator with full schema coverage, the description supplies the missing piece – what the tool returns. Only the role of the region switch (DIN VDE vs NIN/SIA) goes unaddressed in prose.

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

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

Schema coverage is 100% and each parameter already carries title, unit, range and default, so the description can only restate them. It does name three of the four inputs but never mentions the 'region' parameter (DE/CH standards), leaving that choice entirely to 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: it computes the minimum buffer-storage volume from heat output, compressor minimum runtime and permitted spread. What it does is unambiguous, though the opaque sibling names (bot_0xx) give no basis for differentiation and the description makes no attempt to position itself against them.

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

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

There is no statement of when to use this calculator versus alternatives, no prerequisites (e.g. sizing context, standard/region selection), and no exclusions. Usage is only implied by the formula described.

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

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

Annotations already declare readOnly, idempotent and closed-world, so the description doesn't need to carry the safety burden. It does add real value by enumerating the four returned metrics in the absence of an output schema. It does not disclose the underlying sizing method or assumptions (e.g., days of autonomy), which would have pushed this higher.

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

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

Two sentences, front-loaded with the purpose and followed by the output quantities; nothing is wasted. The dense result list is slightly terse but still readable.

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

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

With no output schema, the description correctly compensates by naming each returned value with units. For a purely computational, annotated, fully described parameter set this is nearly complete; only the calculation assumptions 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 100%: every parameter has a title, range, default, and the enum values are explained (including DE = DIN VDE, CH = NIN/SIA). The description adds no parameter-level meaning beyond the listed results, so the baseline 3 applies.

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: sizing a PV battery storage (usable and nominal capacity) from evening/night consumption, and enumerates the result quantities. Very clear about what the tool produces, but the opaque name bot_047 gives no clue and the description does not (and cannot, given opaque siblings) differentiate it from the other bot_* 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?

Usage is implied by the input set (annual consumption, PV power, night fraction), so an agent can infer this is a storage-sizing calculator. However, there is no explicit when-to-use, no prerequisites, and no mention of the alternative tools that presumably cover other PV calculations.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds real value by disclosing what the computation returns (Q in kWh, E_el in kWh, t in h) — important because there is no output schema. It does not mention assumptions (e.g. no heat losses, constant efficiency), which would have earned 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?

Two sentences, zero filler, purpose front-loaded before the result list. Every clause 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 an all-optional calculator with full schema coverage and no output schema, the description supplies the missing return-value information. What is missing is any statement of the model's assumptions or the relationship between the PV-surplus scenario and the given inputs.

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

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

Schema description coverage is 100% with titles, units, ranges and defaults on every parameter, so the schema carries the semantics. The description adds nothing about how T1/T2/eta/P_el/V feed the formulas, and the mention of PV surplus does not map to any actual parameter, leaving that reference unanchored. Baseline 3 applies.

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 ("Berechnen") and a precisely scoped resource: heating time and electricity consumption of a heating rod in a hot water tank. It even enumerates the three output quantities with units. Differentiation from siblings is impossible because every sibling is an opaque bot_XXX identifier, so this is the ceiling for the definition 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?

"auch bei PV-Überschuss" hints at the PV-surplus sizing scenario, but there is no explicit when-to-use/when-not, no prerequisites, and no named alternative among the 30+ siblings. Usage is only implied by the topic.

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

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

Annotations already establish readOnly/idempotent/closed-world, so the safety profile is covered. The description adds that results are derived from Wärmebedarf and JAZ and lists the three returned quantities, but it says nothing about the accuracy of the estimate, unit-conversion assumptions, or that inputs are fully optional with defaults.

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

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

Two sentences, front-loaded with the action and followed by the result set; little waste. The output enumeration is slightly list-like but earns its place given there is no output schema.

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

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

With no output schema, the description does the necessary work of naming the returned values and their units, and the input schema is fully documented. Minor gaps around estimate assumptions are acceptable for a simple pure calculator with all inputs optional.

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

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

Schema description coverage is 100% (including the enum for region and min/max bounds), so the schema carries parameter meaning. The description only echoes two inputs (Wärmebedarf, JAZ) and adds no format, interaction, or defaulting guidance beyond the schema.

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

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

The description names a specific verb (Berechnen) and resource (jährlicher Stromverbrauch und Heizkosten einer Wärmepumpe), and even enumerates the computed outputs. It cannot meaningfully differentiate from siblings since all are opaque bot_XXX names, so it falls just 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?

Use is only implied by the nature of a calculator; there is no explicit statement of when to prefer this tool over another, no prerequisites, and no exclusions (e.g. heat pump types or cases where the estimate is not valid).

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

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

The annotations already declare read-only, idempotent, and closed-world behavior. The description adds useful output behavior by listing daily, monthly, and yearly kWh results plus monthly CHF costs, which matters because there is no output schema. It does not explain formula details, rounding, or how region affects the calculation.

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

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

The description is two sentences, front-loaded with the calculation purpose and followed by the concrete output list. Every sentence contributes information without repetition or 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?

All inputs are fully described by the schema, the annotations cover safety behavior, and the description compensates for the missing output schema by listing the returned metrics. Minor gaps remain around the exact formula, year/month assumptions, and the region parameter's effect on results.

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

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

Schema description coverage is 100%, so all five parameters are fully documented in the schema. The description only names power and operating hours conceptually plus CHF costs, leaving tariff, days_per_month, and region largely implicit. Baseline 3 is appropriate because the schema does the parameter-level work.

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: calculating a device's kWh consumption from power and operating hours. It is clear what the tool does, but the sibling tools are named only as bot_### and therefore cannot be differentiated from this 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?

There is no explicit guidance on when to use this tool versus alternatives, nor any stated prerequisites or exclusions. Usage is only implied by the calculation purpose.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so safety behavior is covered. The description adds useful context by enumerating the calculated outputs and formulas, though it does not discuss assumptions or limitations of the roof geometry 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 purpose is front-loaded in the first sentence and the output list is efficient, with no filler. The second sentence is dense but still structured around computed quantities and units.

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

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

With no output schema, the description appropriately enumerates the return values, including symbols and units. It is nearly complete for a calculation tool, though it does not clarify edge cases such as using alpha alongside g and h.

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

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

Schema description coverage is 100%, so the schema already documents all five parameters including the region enum. The description adds some context by tying g, h, and alpha to specific calculations, but it does not explain the full input semantics or the role of b and region beyond what the schema provides.

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 calculation task with the exact quantities computed: Dachneigung, wahre Sparrenlänge, and Dachfläche. It also lists the specific outputs and their formulas, so the agent can identify precisely what the tool produces.

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 usage by stating the results are a basis for PV-Belegungsplanung, but it does not explicitly say when to use this tool versus alternatives or when not to use it. Usage is inferable from the calculation context rather than stated as a 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?

Annotations already declare readOnly/idempotent/closed-world, so safety is covered; the description adds real behavioral value by enumerating exactly which derived values come back (c_soll, b from a and c_ist, area, perimeter, Δc in mm, actual angle γ). Since no output schema exists, this disclosure is the main source of return-value information.

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

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

Two sentences, purpose front-loaded, followed by a dense but informative enumeration of returned quantities. The list is long but each item earns its place because there is no output schema to carry it.

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

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

For a pure read-only calculation tool with fully documented parameters and no output schema, the description supplies everything an agent needs: inputs, method, use cases, and the complete set of result values. Nothing essential is missing.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds genuine semantics by explaining the input→output relationships (c_soll derived from a and b; b derived from a and the measured diagonal; Δc = c_ist − c_soll). It does not explain the region enum, but the schema description already does that adequately.

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?

A specific verb+resource: it computes the 90° right angle and the target diagonal, and names the concrete application domains (Fundamente, Schalungen, PV-Module) plus the underlying method (Satz des Pythagoras). An agent can tell immediately that this is a geometry/right-angle checker rather than a generic calculator.

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?

Clear usage context is given: use it for foundations, formwork and PV module alignment checks with a simple Pythagorean verification. No exclusions or alternative tools are named, but the sibling names are opaque IDs so there is nothing meaningful to route against.

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

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

The annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false. The description usefully adds the computed result quantities and units, but does not cover precision, validation failures, or other behavioral edge cases.

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

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

Two sentences with a clear front-loaded purpose and result summary. There is no filler; every clause conveys calculation scope, input, or output.

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

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

With no output schema, the description successfully names the output quantities and units, and the parameter schema is fully documented. It is callable as written, though region conventions and rounding or precision behavior are left implicit.

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

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

Schema description coverage is 100%, so all three parameters are already documented. The description mirrors the key inputs (Wirkleistung and cos φ) but does not add syntax, region meaning, or other semantics beyond what the schema provides.

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

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

The description uses a specific verb ('berechnen') and resource ('Blindleistung') and names the inputs (Wirkleistung, cos φ) and outputs (Q, S, φ). The calculation is precisely scoped and distinguishable on its own terms.

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

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

Usage is implied by the stated inputs, but there is no explicit when-to-use guidance, no when-not-to-use guidance, and no named alternatives. Adequate for understanding the calculation context, but not for routing between sibling tools.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds behavioral value by enumerating the four result quantities produced by the calculation, which matters because no output schema exists. It does not discuss assumptions or limits of the model, which keeps it from 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?

Three short sentences: purpose first, then usage hint, then results. Every sentence carries information and the most important content is front-loaded. Slightly dense list in the final sentence but not wasteful.

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

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

With no output schema, the description correctly compensates by listing all four return quantities with units (kWh/a, CHF/a). Combined with fully documented parameters and read-only annotations, an agent has enough to call it correctly; only model assumptions 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 100% and all six parameters carry titles, units, ranges and defaults, so the schema does the heavy lifting. The description only loosely references 'Leistung', 'Standortertrag' and 'eigene Tarife' and adds no detail beyond the schema (e.g. no guidance on choosing region or self-consumption share). Baseline 3 applies.

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 opens with a specific verb+resource: 'Berechnen Sie den Jahresertrag einer PV-Anlage in kWh'. It also names the inputs (Leistung, Standortertrag) that drive the calculation. Sibling names are opaque identifiers (bot_0xx), so sibling differentiation cannot be expressed, but the purpose itself 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?

Usage is only implied: the second sentence hints that self-consumption and revenue can be estimated with one's own tariffs, implying the tool is for yield/ROI estimation. There is no explicit when-to-use, when-not-to-use, or named alternative among the 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?

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so safety is covered; the description then adds meaningful behavioral context by disclosing exactly which derived values are returned (k_In, I_n2,max, ΔI_k, utilization %, recommended I_n1). For a stateless calculation tool this is solid added value beyond the annotations.

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

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

Two sentences: the first front-loads the purpose, the second lists outputs. Efficient, though the output enumeration is dense and formula-heavy enough that it flirts with over-packing a single 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?

With no output schema, the description correctly carries the return-value burden and enumerates the result quantities with units and constraints. Combined with full schema coverage of inputs and clear annotations, an agent has enough to call it correctly; only explicit when-to-use framing is missing.

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

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

Schema description coverage is 100%, so the baseline is 3; the description earns above that by supplying the governing formula and constraint (k_In = I_n1/I_n2, required ≥ 1,6; I_n1 ≥ 1,6·I_n2), which explains the relationship between in_vor and in_nach rather than just restating the fields. It does not explicitly map every named concept to its parameter name, keeping it just short of a 5.

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 precise verb ('Selektivität ... prüfen') and a specific resource pair (SLS-Schalter/Vorsicherung vs. nachgeordneter LS-Schalter), and enumerates the computed quantities. An agent immediately knows this is a selectivity-check calculation, not a generic electrical helper. Siblings are opaque codes so name-based differentiation is impossible, but the purpose is unambiguous on its own.

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 the usage context (checking selectivity between two protection devices) but never states when to prefer this tool over alternatives, prerequisites (e.g. needing manufacturer table data for I_s), or exclusions. Guidance is inferable from the purpose, not 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?

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description usefully discloses the return values (yearly self-consumption, grid feed-in, CHF savings), which adds value beyond annotations. It does not address defaults, unit assumptions, or the CHF-vs-DE currency mismatch visible in the schema.

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

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

Two sentences, no filler: the action comes first, followed by the concrete output list. Appropriately sized for a five-parameter calculator with no output schema.

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

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

There is no output schema, and the description compensates by enumerating the three returned metrics with units. Combined with the richly documented input schema and the read-only annotations, an agent has enough to invoke it correctly; only default behavior and currency semantics remain implicit.

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

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

Schema description coverage is 100%, with titles, enums, defaults, and min/max on every property, so the baseline is 3. The description adds no parameter-level explanation (e.g. what self_consumption_rate influences), so it cannot exceed the schema's contribution.

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 (berechnen) and resource (PV-Eigenverbrauch, Stromkostenersparnisse) and even names the three result metrics, so the agent knows exactly what the tool produces. It cannot be distinguished from siblings, but the sibling names (bot_060 etc.) are opaque IDs that offer no differentiation opportunity.

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

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

Usage is implied by the nature of a calculator ('Berechnen Sie ... einfach mit diesem Rechner'), but there is no explicit when-to-use guidance, no prerequisites, and no reference to any alternative tool. Adequate but leaves the agent to infer the context.

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

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

The annotations already establish readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds useful return values, q_b and w with units, but omits assumptions, formula context, and the effect of the region parameter.

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 short and front-loaded, with the result values clearly stated in the final sentence. Minor waste appears in 'einfach online', and the region/title tension is left unaddressed.

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?

Because there is no output schema, the description appropriately names the returned quantities and units. However, it does not reconcile the Swiss SIA 261 framing with the region parameter defaulting to DE, which is a meaningful ambiguity for invocation.

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

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

Schema description coverage is 100%, so all five parameters and the region enum are already documented in the schema. The description mentions aerodynamic coefficients and dynamic pressure conceptually but adds no parameter-level syntax or default behavior beyond the schema.

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

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

The description states a specific verb and resource: calculating wind load according to SIA 261 for structures in Switzerland. The domain is clear, though the opaque sibling names bot_009–bot_065 provide no basis for explicit differentiation.

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 says what the tool calculates but gives no when-to-use guidance, no prerequisites, and no alternatives. The phrase 'einfach online' is promotional rather than operational guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds the output dimension ('Benötigte Ladeleistung [kW]'), which is useful since there is no output schema. However, it is silent on how the efficiency parameter (70–100%) affects the calculation and what the result format looks like beyond the unit.

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, front-loaded with the goal and ending with the result. Minor redundancy: 'benötigte Ladeleistung' in sentence one is rephrased as 'passende kW-Zahl' in sentence two, which adds little. Overall efficient and clear.

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

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

The tool has four optional parameters (all with defaults), no output schema, and a simple read-only calculation. The description states the result unit but never explains defaults, what happens when parameters are omitted, or how efficiency factors into the formula. The 100% schema coverage carries much of the load, but for a calculation tool the semantics of the formula remain undisclosed.

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

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

Schema description coverage is 100%, so the schema already carries all parameter meaning. The description names two of the four inputs (Akkukapazität, Ladezeit) but omits efficiency and region, which materially affect the calculation. Given complete schema coverage, this baseline of 3 is appropriate, with no added value in description.

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

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

States a specific verb and resource: it calculates the required charging power (Ladeleistung) for a wallbox based on battery capacity and desired charge time. This is clearly distinguishable from the opaque bot_XXX siblings. It doesn't differentiate from any named sibling, but the purpose is unmistakable.

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 usage through the calculation inputs (capacity and desired charge time), but it never states when to choose this tool or when not to. With all siblings being opaque bot_XXX names, the lack of any routing guidance leaves the agent to infer the use case from context alone.

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

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

The annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered and the description only needs to add domain behavior. It does contribute the standard, the physical meaning and the two output quantities with units (qp, we in kN/m²), which is genuinely useful, but it says nothing about the underlying formula, how defaults are applied, or how out-of-range values are handled.

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

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

Two sentences, zero padding: the first states purpose, standard and application, the second enumerates the return quantities with units. It is front-loaded and every clause carries information.

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

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

With no output schema, the description compensates by naming the returned quantities and their units, which is exactly what an agent needs to know. What remains thin is the engineering decision context – the description does not hint at how region and the pressure coefficient interact, though the schema covers the fields themselves.

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

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

Schema description coverage is 100% – all three parameters carry titles, ranges and descriptions – so the schema does the explanatory work. The tool description adds no parameter-level guidance at all (e.g. which cpe,10 value suits which surface type, or practical vb,0 ranges per region), so the baseline of 3 applies.

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 and resource pair ('charakteristischen Winddruck und die daraus resultierende Windlast berechnen') and anchors it to the governing standard DIN EN 1991-1-4. It does not differentiate itself from any sibling, which is impossible here since all siblings are opaque identifiers like bot_009/bot_064, so the ceiling is a 4.

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?

'für statische Nachweise' gives an implied application context, so a reader knows roughly when the tool applies. But there is no statement of when not to use it, no prerequisites (e.g. required input data), and no pointer to any alternative among the 37 sibling tools.

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

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

Annotations already state readOnlyHint, idempotentHint and openWorldHint=false, so safety and repeatability are covered. The description adds value by naming the two output quantities (s and sd in kN/m²), which the annotation set cannot express. However, it omits the actual relations (s = µ1·Ce·sk, sd = γQ·s) and says nothing about defaults being applied when parameters are omitted — notable since all five parameters are optional.

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: purpose, audience/type, then outputs. The result list is front-loaded where it matters and there is no filler. Slightly weakened by the vague marketing phrase 'Einfacher Online-Rechner', which occupies space without informing an agent.

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

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

With no output schema, the description correctly absorbs the return-value burden by listing s and sd. But it leaves a real gap: the schema offers region DE/CH (DIN vs NIN/SIA) while the description only cites ÖNORM EN 1991-1-3, so an agent cannot tell which standard applies for CH. Default behavior for the five optional parameters is also unaddressed.

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

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

Schema description coverage is 100%, so the baseline of 3 applies; the schema already documents every parameter with units and ranges. The description contributes no additional semantics about how sk_boden, formbeiwert_basis, expositionsbeiwert and teilsicherheitsbeiwert combine, nor how 'region' changes the applicable code.

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 ('Berechnen Sie die Schneelast auf Dächern') plus the governing standard (ÖNORM EN 1991-1-3) and the two results produced. An agent knows exactly what computation this performs. It cannot differentiate from siblings, but the sibling names (bot_009 … bot_065) are opaque tokens that carry no semantics, so nothing more is achievable 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?

The standard reference and the phrase 'Einfacher Online-Rechner' imply the use case (quick characteristic/design snow load per EN 1991-1-3), but there is no explicit when-to-use, when-not-to-use, or named alternative. Nothing tells the agent whether this supersedes or complements other structural tools in the sibling set.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds real context beyond that: the Darcy-Weisbach model and the four returned quantities (velocity, Reynolds number, lambda, pressure loss) including units, which matters since there is no output schema. It stops short of noting limitations such as fittings or non-straight pipe segments.

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, front-loaded with the action, then the model, then the outputs. Only the 'einfach online' phrase is dead weight.

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-required-parameter calculation tool with no output schema, the description supplies the missing return-value information and names the governing model. All inputs are covered by the schema, leaving only minor gaps such as handling of defaults or validity limits of 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 100% with units and ranges documented for all six parameters, so the schema carries the parameter burden. The description adds nothing about the inputs themselves, which matches the baseline of 3 for a fully documented schema.

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

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

The description states a specific verb and resource ('Druckverlust in geraden Rohrleitungen berechnen') and names the underlying model (Darcy-Weisbach), so an agent knows exactly what computation is performed. Sibling tools are opaque bot_NNN identifiers, so no differentiation is possible or expected, which keeps this just 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?

There is no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions beyond the implicit 'gerade Rohrleitungen' scope. 'einfach online' is marketing filler rather than routing guidance.

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