engineering

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

With no annotations provided, the description carries full burden for behavioral transparency. It lists outputs but does not disclose any side effects, permissions needed, data sources, or limitations. The description lacks detail on how the assessment is performed or any constraints.

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

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

The description is a single sentence that is clear and front-loaded. It avoids unnecessary words but could be slightly more structured. It is concise without being 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?

Given the tool has 7 required parameters and no output schema, the description is too brief. It does not explain return values format, error conditions, or constraints (e.g., valid country list). This is insufficient for an agent to fully understand the tool's behavior.

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 43% (below 50%), so the description should compensate but does not. It adds no extra meaning beyond the minimal schema descriptions (e.g., examples for country, building_type). The description only mentions outputs, ignoring parameter semantics entirely.

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

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

The description clearly states the verb 'assess' and the resource 'EU EPBD (2024) compliance', listing specific outputs (compliance score, renovation cost estimate, deadline pressure, priority retrofit measures). This distinguishes it from sibling tools that focus on carbon footprint, readiness, or other calculations.

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 does not provide any guidance on when to use this tool versus alternatives. It mentions EU EPBD compliance but no exclusions, prerequisites, or comparisons to sibling tools like building_carbon_footprint or calculate_carbon.

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

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

No annotations provided, so description bears the burden. It discloses that it returns per-scope emissions, compliance, gap analysis, and actions. However, it does not specify whether it is read-only, requires permissions, or has other behavioral traits (e.g., real-time vs cached, data refresh).

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?

Description is a single dense sentence that front-loads key capabilities. It is concise but could benefit from structured formatting (e.g., bullet points) for better readability.

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 high complexity (10 params, no output schema, no annotations), the description lists outputs but lacks parameter details and return format. It partially compensates with output enumeration but remains incomplete for optimal tool invocation.

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

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

Schema description coverage is 0%, and the description does not explain any parameters beyond their names. With 10 parameters (many opaque like heat_kwh_year, renewable_pct), the lack of parameter semantics makes it hard for an agent to correctly populate inputs.

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?

Describes computing building carbon footprint with Scope 1/2/3, CRREM stranding check, and embodied carbon. Lists specific outputs (per-scope tCO2e, intensity, CRREM compliance, net-zero gap, priority actions). Clearly distinguishes from sibling tools like calculate_carbon and uae_climate_ghg.

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 guidance on when to use this tool vs alternatives. The description implies it's for comprehensive carbon footprint assessment, but does not mention exclusions or differentiate from similar sibling tools (e.g., calculate_carbon).

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

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

With no annotations, the description bears full burden. It discloses the tool returns a score, complexity, domain scores with RAG, and recommendations, implying a read-only assessment. It does not mention any destructive actions or authorization needs, which is acceptable given the tool's nature. 'RAG' is not expanded, but contextually clear.

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

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

The description is a single, well-structured sentence that immediately states the tool's purpose and enumerates key outputs. No fluff or redundant information—every part contributes to understanding the tool's function.

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

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

Given 8 required parameters and no output schema, the description adequately covers the output structure: a readiness score (0-100), project complexity, four domain scores with RAG, and recommendations. This provides sufficient context for selecting and using the tool.

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

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

Schema description coverage is 0%, meaning the description must compensate. However, it does not list or explain the 8 required parameters beyond implicitly referencing inputs via domain scores. The parameter names and enums are self-explanatory, but the description adds no new semantic value (e.g., how ‘condition’ or ‘location’ affect scoring).

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?

Description clearly states the tool assesses 'Building Readiness assessment for change-of-use / conversion' and lists specific outputs (readiness score, complexity, domain scores with RAG). This distinguishes it from sibling tools like building_carbon_footprint (carbon-focused) or dgnb_bim_readiness (BIM-specific), establishing a unique purpose.

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 context is implied (change-of-use assessment) but there is no explicit guidance on when to use this tool versus alternatives like uk_planning_checker or mees_checker. The description does not mention prerequisites or exclusions, leaving the agent to infer appropriate scenarios.

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

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

No annotations are provided, so the description carries the full burden. It discloses the type of calculation (operational + embodied carbon) and the outputs, but does not mention any safety considerations, data dependencies, or side effects. It adequately indicates a read/calculation operation, not a destructive one.

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: the first specifies the action and methodology, the second details the outputs. It is concise, front-loaded, and contains no extraneous 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 tool with 5 parameters and no output schema, the description provides a good overview of what it does and what it returns. It mentions standards and output types, which helps the agent understand the tool's scope. However, it does not explain how parameters like construction_year influence the calculation or the meaning of 'net-zero gap', leaving some gaps for full understanding.

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 60%, meaning some parameters (country, building_type, energy_kwh_year) have descriptions. The tool description does not add any additional meaning beyond what the schema provides for those, nor does it explain the undocumented parameters (floor_area_m2, construction_year). Baseline 3 is appropriate as description offers little added value.

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 'Calculate operational + embodied carbon and net-zero gap' referencing specific standards (CIBSE TM65 / RICS WLCA), and mentions specific outputs (carbon intensity, benchmark, reduction measures with payback). This distinguishes it from sibling tools like 'building_carbon_footprint' which may not include net-zero gap or payback analysis.

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 used for carbon calculations following specific standards, but does not explicitly state when to use it vs. alternatives like 'building_carbon_footprint' or 'assess_epbd_score'. No exclusions or prerequisites are mentioned.

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

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

No annotations are provided, so the description carries full burden. It discloses that the tool returns PUE score, efficiency rating, annual cost estimate, and recommendations, but omits details like handling of invalid inputs, computational implications, or any side effects.

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

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

The description is a single, well-structured sentence that front-loads the main action and output. It is concise, using about 20 words, though it could include brief usage context without losing conciseness.

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

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

With 4 required parameters, no output schema, and no annotations, the description provides a fair overview but lacks details on output format, expected parameter ranges, or prerequisites. The schema covers parameter units, but contextual completeness is average.

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 each parameter having a clear description and example in the input schema. The tool description adds no additional parameter information beyond the schema, meeting the baseline of 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?

The description clearly states the tool calculates Power Usage Effectiveness (PUE) for data centres or server rooms, using specific verb 'Calculate' and resource 'PUE'. It distinguishes from sibling tools like 'calculate_carbon' or 'estimate_cooling_load' by focusing on PUE, a unique metric.

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 for data centre or server room PUE calculations, but provides no when-not-to-use guidance or alternative tools. Sibling tools exist for related energy metrics, but no comparisons are made.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions return outputs (feasibility score, timeline, etc.) but does not state side effects, data modification, or prerequisites. The tool likely performs a read-only assessment, but this is not confirmed.

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

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

The description is a single sentence that efficiently states the core purpose and key outputs, with no unnecessary words. It is front-loaded 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?

Given no output schema, the description adequately lists five output types (feasibility score, timeline, voltage, substation requirement, next steps). However, it does not cover edge cases or dependencies for the 6 input parameters, which would improve completeness.

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

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

Schema description coverage is 0%, meaning parameter descriptions are missing from the schema. The tool description does not elaborate on input parameters, leaving the agent to infer meanings from parameter names alone (e.g., site_location, intended_use). For 6 parameters, this is insufficient.

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

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

The description clearly states the tool assesses UAE grid connection feasibility, listing specific utility authorities (DEWA/ADDC/SEWA/FEWA) and outputs. This distinguishes it from sibling tools which cover different domains like EPBD, BIM, carbon, etc.

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 use for grid connection feasibility assessment in UAE but does not explicitly state when to use versus alternatives or when not to use. Sibling tools like get_technical_dd_quote exist for detailed design, and no guidance is given on differentiation.

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

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

No annotations provided, so description carries full burden. It discloses return values (score, maturity, fine, remediation) but does not state whether the tool is read-only or has side effects, nor any behavioral constraints like rate limits or authorization needs.

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

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

The description is a single, informative sentence that front-loads purpose and outputs. It is concise but could benefit from slight structuring (e.g., listing outputs).

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

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

Given the complexity (11 required parameters, no output schema, no annotations), the description is too minimal. It lacks guidance on how to provide inputs or interpret results, making it insufficient for an agent to use effectively.

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 only 9% (only sector has a description). The description does not explain any parameters beyond what the schema provides, offering no additional meaning for the 11 required inputs.

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

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

The description clearly states the tool assesses NIS2 Directive compliance readiness and lists specific outputs (compliance score, maturity level, fine exposure, remediation actions). It distinguishes from sibling tools which address other regulations (e.g., EPBD, UAE BIM, UK planning).

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

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

No guidance on when to use this tool versus alternatives, nor any prerequisites or limitations. The description only states what it does, not when it should be invoked.

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

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

No annotations are provided, so the description carries the full burden. It does not disclose behavioral traits such as authentication needs, rate limits, side effects (e.g., read-only), or whether external API calls are made. The tool's behavior beyond returning results is opaque.

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

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

The description is a single, efficient sentence that front-loads the key action and scope. It could be slightly more structured (e.g., listing parameters), but it is not verbose and every part adds value.

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 8 required parameters, no output schema, and moderate complexity (UAE BIM mandates), the description provides minimal context. It mentions return items but does not specify their format, data types, or error conditions. There are gaps in prerequisites (e.g., need a BIM model? BEP?). It is adequate but not thorough.

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 only 13% (2 out of 8 parameters have enums documented, but no further description). The description adds no parameter-level meaning beyond what the schema provides. For such low coverage, the description should compensate by explaining parameter roles or relationships, which it does not.

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

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

The description clearly states the tool checks UAE BIM mandate applicability, names specific circulars (Dubai Circular 196, Abu Dhabi DMT, Sharjah), and lists return items (mandate status, compliance score, required LOD, submission checklist). It uses a specific verb-resource combination and distinguishes itself from sibling tools like building_carbon_footprint or check_uae_cybersecurity.

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 context (UAE BIM compliance) but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or when-not-to-use cases. No alternatives are mentioned, so the agent must infer from the tool name and description.

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

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

No annotations provided, so the description bears full burden. It mentions return values (framework, score, gaps, controls), but does not disclose side effects, authentication needs, rate limits, or data destruction. Some behavioral context is given but not comprehensive.

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

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

The description is a single, front-loaded sentence that efficiently conveys the tool's purpose. However, it could include more structured details without being verbose, so it is concise but not maximally informative.

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

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

With 8 required parameters, no output schema, and no annotations, the description is too brief. It does not explain how parameters relate to the output or how to interpret the boolean flags. The tool's complexity demands more contextual detail.

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 only 13%, with only the 'emirate' parameter described. The description does not explain the meaning or impact of any parameter (e.g., has_isms, has_incident_response). Given low coverage, the description should compensate but fails to add value 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 clearly states the tool's purpose: assessing UAE cybersecurity regulatory compliance across specific frameworks (NESA IAS, Dubai ISR, CBUAE, TDRA) and returning framework, score, gaps, and controls. It uses a specific verb and resource, distinguishing it from siblings like check_nis2_readiness.

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 guidance on when to use this tool versus alternatives like check_nis2_readiness or other siblings. The description implies UAE-specific compliance, but lacks exclusion criteria or context for when not to use it.

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

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

With no annotations, the description carries full burden. It discloses it flags blocking failures and returns recommended checks, but does not mention potential side effects, authorization needs, or whether it is idempotent.

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: first defines purpose and scope, second clarifies limitations. No wasted words; front-loaded with key 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?

No output schema is provided, so description should hint at return value. It mentions flags and recommended checks, but does not explain the scoring output, how 'purpose' enum affects results, or structure of the response.

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 parameters described in schema). The description adds context about the checklist categories but does not elaborate on parameter values or format beyond what 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 clearly states the tool's purpose: NIS2/EPBD contractor vetting using a 12-question checklist across four categories. It distinguishes itself from siblings like check_nis2_readiness and assess_epbd_score by focusing on contractor-level assessment.

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

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

The description implies when to use (contractor vetting) and states it is not a formal due-diligence report, but lacks explicit guidance on when to choose this over sibling tools like check_nis2_readiness or assess_epbd_score.

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

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

No annotations are provided, so the description must convey behavioral traits. It states the tool is a self-assessment and returns certain results, but does not disclose whether it is read-only, requires authentication, or has side effects. For a simple assessment tool, the lack of explicit non-destructive or stateless claims leaves some ambiguity.

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 only: first defines core functionality and outputs, second clarifies it is not a formal audit. Every sentence earns its place; no fluff. Front-loaded with essential 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 tool with no output schema, the description partially covers return values but lacks structure details (e.g., JSON fields). It does not mention any prerequisites or limitations beyond 'not a formal audit'. Given the moderate complexity and 2 parameters, the description is adequate but leaves some gaps.

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

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

Input schema has 100% description coverage, so baseline is 3. The description adds value by explaining what the tool returns (pre-score, levels, breakdown), which contextualizes the parameters. It does not add new parameter-level details but clarifies the overall purpose of the assessment.

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 identifies the tool as a self-assessment for DGNB pre-score and BIM maturity, specifies the 20-question checklist, and lists returned outputs. It distinguishes from a formal audit and from sibling tools like building_readiness or check_uae_bim_compliance by name-dropping specific standards (DGNB, ISO 19650).

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 early-stage self-assessment ('Not a formal DGNB audit') but does not explicitly state when to use it vs. alternatives. No exclusion criteria or prrequisites are mentioned, which would help agents choose among sibling tools like check_uae_bim_compliance or building_readiness.

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

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

No annotations are provided, so the description carries full burden. It only says 'Indicative,' hinting at approximate outputs, but does not disclose whether the tool is read-only, destructive, or any rate limits. For a tool that likely generates a non-destructive output, more transparency is needed.

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 sentence with a parenthetical list, efficiently front-loading the core concept 'EPBD-style staged digital renovation passport.' It covers key outputs without redundant phrases, though splitting into a short paragraph could improve readability.

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

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

No output schema exists, so the description must hint at return value structure. It mentions 'cost ranges, energy savings and EPC trajectory' which is helpful but does not specify format (JSON, text, etc.), nor does it explain how optional parameters affect the roadmap. For a tool with 7 parameters, the description is incomplete.

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%. The description mentions 'current EPC, floor area and heating type' which map to required parameters but adds no new meaning beyond the schema's own descriptions. Optional parameters like 'era', 'address', 'country', 'building_type' are described in schema as 'label only,' but the description doesn't clarify their role.

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

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

The description clearly states the tool produces an 'EPBD-style staged digital renovation passport' with a '3-phase roadmap' and lists outputs (cost ranges, energy savings, EPC trajectory). It uses specific verbs (implies 'generate') and a clear resource, distinguishing it from sibling tools like 'assess_epbd_score' or 'building_carbon_footprint which focus on assessment rather than a staged roadmap.

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 guidance on when to use this tool versus alternatives. The description implies it is for renovation planning, but does not specify prerequisites (e.g., having an EPC rating), exclusions (e.g., not for new builds), or mention other tools as 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?

With no annotations, the description carries full burden. It transparently states the tool determines scope and computes KPIs, and notes that regulation mandates reporting, not targets. This is sufficient for a computation tool; no side effects are mentioned but none are expected.

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 concise (two sentences), front-loaded with regulatory context, and efficiently communicates purpose and behavior without redundancy.

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

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

Given no output schema and 6 parameters, the description covers the tool's role (determine scope, compute KPIs) and regulatory basis. It could be slightly more explicit about output format or conditional behavior for low power, but overall it is sufficiently informative.

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 descriptors already explain each parameter. The tool description adds overall context (directive, KPI names) but does not significantly enhance parameter meaning 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 clearly states the tool determines reporting scope based on IT power threshold and computes mandated KPIs (PUE, WUE, ERF, REF). It distinguishes itself from siblings like 'calculate_pue' by covering a full reporting pack with multiple KPIs and scope determination.

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 provides context by referencing the specific EU directive and regulation, and clarifies that the tool is for reporting compliance rather than target values. It implicitly indicates when to use (for EU data centre reporting) but does not explicitly exclude alternatives or state when not to use.

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

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

With no annotations, the description bears full responsibility for behavioral disclosure. It mentions methodology and outputs but does not disclose whether the tool is read-only, requires external data, or has side effects. Essential behavioral traits are omitted.

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 concise sentences that immediately convey the tool's purpose, methodology, and outputs. Every part adds value with no redundancy.

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 six required parameters with sparse descriptions and no output schema, the description is insufficient for full autonomous use. The agent would likely need to infer or request additional details.

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

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

Schema description coverage is only 17% (one parameter). The description does not explain the remaining five parameters beyond their names and types, leaving the agent without sufficient guidance to populate them correctly.

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

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

The description clearly states the tool estimates cooling load using standard methodologies (CIBSE/ASHRAE) and lists output types. However, it does not distinguish this tool from the sibling 'thermal_load', which likely performs a similar function.

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 is provided on when to use this tool versus alternatives, nor are there any prerequisites or exclusions. The agent must infer usage from the tool name and description 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?

No annotations are provided, so the description must fully disclose behavior. It accurately describes the tool as providing an indicative parametric estimate without side effects. It does not mention any destructive actions or special permissions, but the informational nature is clear.

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

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

The description is concise with two sentences: the first covers purpose and parameters, the second describes outputs and a caution. No redundancy, and it front-loads key 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?

Given the absence of an output schema and annotations, the description adequately outlines inputs and outputs (cost ranges and breakdown). However, it omits details on the breakdown structure and specific limitations beyond the indicative nature. It is sufficient but not thorough.

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 only 43% (3 of 7 parameters documented). The tool description lists the parameters (country, project type, etc.) but does not explain enum values or parameter semantics beyond the schema. This leaves gaps for parameters like 'bim', 'specification', etc.

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

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

The description clearly states the tool provides parametric construction cost benchmarks across regions and project dimensions, and returns per-m2 and total cost ranges with a breakdown. It distinguishes itself from sibling tools, which focus on other building assessments.

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 notes the estimate is indicative and advises validation against current cost indices, giving a usage caution. However, it does not explicitly specify when to use this tool versus alternatives or provide exclusions, leaving the agent to infer from 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?

No annotations are provided, so the description carries full burden. It only states that the tool 'selects a section, computes...' but does not disclose behavioral traits such as how section selection works, default assumptions, required permissions, or any side effects. The 'indicative' caveat adds some transparency but is insufficient.

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-loading the core purpose and key details. Every sentence provides value: material options, computed checks, and the indicative disclaimer. No redundant explanations.

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

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

Given the tool's complexity (9 parameters, 3 materials, multiple checks) and lack of output schema, the description adequately covers what the tool does but omits what it returns (e.g., selected section, utilization factors). The 'indicative' label partially compensates, but more detail on outputs would improve completeness.

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

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

All 9 parameters have descriptions in the input schema (100% coverage), so the schema itself is informative. The tool description adds minimal additional meaning beyond restating that loads are characteristic. Baseline score of 3 is appropriate as the description does not compensate for any gaps.

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

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

The description explicitly states it's for preliminary Eurocode beam design (steel EC3, composite, concrete EC2), enumerates the computations (ULS bending/shear, SLS deflection, fire protection), and clarifies it's indicative. It clearly distinguishes from the sibling 'eurocode_column_checker' by focusing on beams.

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 notes this is a 'preliminary' and 'indicative' design for early-stage work, implying it is not for final stamped designs. However, it does not explicitly specify when to use this tool versus alternatives (e.g., other beam design tools) or provide exclusion criteria beyond the indicative nature.

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

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

No annotations are provided, so the description must disclose behavioral traits. It states the tool is 'indicative' and lists outputs, which sets expectations. However, it does not mention whether the tool is read-only, has side effects, or any performance limitations. For a calculation tool, the lack of explicit safety info is acceptable but not fully transparent.

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 concise: two sentences. The first sentence states the tool's purpose and standards, the second lists outputs and a caveat. It is front-loaded with the most critical information and contains no redundant words. Every sentence serves a purpose.

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

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

Given no output schema, the description lists key outputs (Ncr, slenderness, chi, NRd, utilisation). It covers the two material types (steel and concrete) and references relevant Eurocode sections. It could explicitly mention that both materials are handled in a single call and clarify the required parameters for each, but overall it provides sufficient context for basic usage.

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%, meaning all parameters have descriptions. The overall description adds context by referencing Eurocode clauses and clarifying the scope (steel vs. concrete), but does not elaborate on individual parameters beyond what the schema already provides. The connection between parameters and material types is partially conveyed through param descriptions.

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

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

The description states it performs Eurocode axial column buckling check for steel (EC3) and concrete (EC2), listing outputs (Ncr, slenderness, chi, NRd, utilisation). It is clear about the general function but does not explicitly differentiate from sibling tools like 'eurocode_beam_designer' or 'thermal_load'. The mention of specific Eurocode clauses adds precision.

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 includes a caveat ('Indicative, not a stamped design') but lacks explicit guidance on when to use this tool versus alternatives. It does not state prerequisites or scenarios (e.g., 'use for columns only'). The purpose is implied but not detailed enough for an agent to confidently select it over related tools.

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

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

No annotations provided. Description states output is 'indicative' and includes fee ranges, turnaround days, and CTA, but does not disclose authorization needs, rate limits, or non-destructive nature. Adequate but minimal.

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?

Single concise sentence, front-loaded with the core purpose. No unnecessary text, but could benefit from structure like a bulleted list of outputs.

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

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

For a tool with 6 complex parameters and no output schema or annotations, the description is too sparse. It omits details on how inputs affect the estimate, any limitations (e.g., minimum area, geography constraints), and the exact output format.

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 17% (only building_type has a description). Description does not clarify the meaning or influence of parameters like gross_area_m2, timeline_weeks, or disciplines. Fails to compensate for low schema coverage.

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?

Specifies the action ('Generate an indicative TDD fee estimate') and the resource (fee estimate for Technical Due Diligence). Clearly distinguishes from sibling tools like 'calculate_carbon' or 'eu_cost_benchmarking' by its fee estimation purpose.

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?

Implied usage: use when needing a TDD fee estimate. No explicit when-not or alternative suggestions, though sibling tools cover other domains. Lacks direct guidance on when to choose this over others.

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

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

No annotations provided, so description carries full burden. It discloses that values are typical U-values/SCOP (not measured), returns design heat loss, recommended output, indicative SCOP, and annual demand. This informs the agent about the estimation nature and output format.

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: first states purpose and key inputs, second lists outputs and caveat. No redundant information; every sentence adds value.

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 10 parameters and no output schema, the description covers purpose, inputs, outputs, standards, and a caveat about typical values. It is sufficient for an agent to understand the tool's scope and 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 coverage is 60%, with some parameters having descriptions. The description adds overall methodology context (fabric + ventilation, based on floor area, storeys, age band, location, glazing) and lists outputs, compensating for missing parameter details.

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?

Description clearly states it estimates domestic whole-dwelling fabric and ventilation heat loss for heat pump sizing, referencing BS EN 12831/MCS standards. It distinguishes from sibling tools like 'thermal_load' by specifying the application (heat pump sizing) and typical U-values approach.

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?

Description indicates usage for heat pump sizing and lists input parameters like floor area, age band, location, and glazing. It does not explicitly state when not to use or alternative tools, but the purpose is clear enough to infer appropriate 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?

Details what the tool returns: compliance, can-let, cost cap, and penalties, and clearly notes the proposed EPC C uplift is advisory only. Since no annotations are provided, the description carries the full burden and does so adequately.

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?

Description is concise, front-loading the purpose. It is a single paragraph but effectively covers key aspects without excess verbiage.

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 mentions return values (compliance, can-let, cost cap, penalties) but does not explain them. The tool is simple with two enums, but more detail on the proposed uplift's advisory nature and what 'cost cap' and 'penalties' entail would improve completeness.

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

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

Schema description coverage is 0%, so the description should compensate. However, it does not explain the parameters beyond what the schema already provides (enums for property_type and current_epc_band). The meaning or implications of different values are not elaborated.

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?

Description clearly states it performs an MEES check for England & Wales, testing against the current EPC E minimum and proposed EPC C uplift. The verb 'check' and resource 'MEES' are specific, and it distinguishes from sibling tools like uk_planning_checker.

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

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

Explicitly states it is for private rented property in England & Wales, providing clear context. However, it does not explicitly mention when not to use or name alternative tools for similar checks.

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

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

No annotations are provided, so the description carries full burden. It discloses that the tool returns pass/fail and points to TM59, but it does not mention whether the check is read-only, what inputs are required, or any side effects. The word 'Indicative' hints at accuracy but not behavioral traits.

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 long and contains no redundant information. It is front-loaded with the purpose and then details the checks and outcome. However, it could be more structured for clarity.

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

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

Given the complexity (6 parameters, no output schema, no annotations), the description is adequate but leaves gaps. It does not explain the calculation logic, assumptions, or limitations of the simplified method, nor does it describe the return format beyond pass/fail. The reference to TM59 adds context, but more detail would improve completeness.

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 33%, which is low. The description summarizes that the tool tests maximum glazing area by orientation, risk zone, cross vs. single aspect, and minimum free ventilation area, which maps to several parameters. However, it does not explain each parameter individually, so the value added over the schema is moderate.

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

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

The description clearly states the tool performs a UK Approved Document O 2021 simplified-method overheating check for new residential buildings, specifically testing maximum glazing area and minimum free ventilation area. It returns pass/fail and mentions referral to CIBSE TM59, making the verb and resource specific and distinct from sibling tools.

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

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

The description implies usage for the simplified method of Document O and notes that CIBSE TM59 modeling is needed if it fails, but does not explicitly state when not to use this tool or mention alternatives among the sibling tools. The term 'Indicative' hints at limitations but no clear exclusions.

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

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

With no annotations, the description carries full burden. It discloses the regulatory reference (UK Approved Document S 2021) and notes that outputs are 'Indicative', hinting at limitations. However, it does not detail error conditions, dependencies, or computational behavior beyond stating what is returned.

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

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

The description is a single, concise paragraph with the most important information front-loaded. It contains no fluff, but could be slightly more structured (e.g., separating inputs and outputs) for easier scanning.

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 calculator tool with 5 parameters and no output schema, the description covers the essential outputs (charge points, cable routes, power, cost caps) and applicable regulations. It is adequate for an AI to understand the tool's function, though exact output format is not specified.

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

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

The input schema covers 60% of parameters with descriptions. The description adds context for 'cable routes (1-in-5 for non-residential)' which is not a direct parameter, but overall the parameters (works, building_type, parking_spaces, etc.) are self-explanatory from the schema. The description does not significantly enhance parameter understanding 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 clearly states it is a calculator for UK Approved Document S 2021 electric-vehicle charge-point requirements, specifying the use cases (new build and major renovation, residential and non-residential) and outputs (charge points, cable routes, power, cost caps). This uniquely identifies the tool among siblings, which cover different building regulation topics.

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 explicitly lists the applicable contexts (new build, major renovation, residential, non-residential) but does not specify when to avoid using it or mention alternative tools. The sibling list provides context but no direct comparison.

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

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

No annotations are provided, so the description carries full burden. It does not disclose behavioral traits such as idempotency, side effects, authorization needs, or rate limits. The description only lists outputs, missing important context for safe invocation.

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

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

The description is a single sentence that front-loads the purpose and lists outputs. It is concise but lacks structural elements like bullet points or sections. Every part is earnful, though the list of outputs could be more organized.

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 6 parameters and no output schema, the description is somewhat incomplete. It lists outputs but not their format or units, and does not explain the calculation logic. However, the tool is fairly standard (ROI calculator), so the missing context is partially acceptable.

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 only 50% (manual_hours, software_cost, efficiency_gain_pct have descriptions). The description does not add any parameter meaning beyond what the schema provides; it only lists outputs. It fails to compensate for the missing parameter descriptions.

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

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

The description clearly states it is an ROI calculator for engineering and lists the outputs (current manual cost, annual saving, etc.), making the purpose understandable. However, it does not explicitly describe the input-output relationship or differentiate from siblings beyond being a financial calculation tool.

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

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

No guidance on when to use this tool versus the many sibling tools (e.g., assess_epbd_score, building_carbon_footprint). It does not mention context, prerequisites, or when not to use it.

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

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

With no annotations, the description must disclose behavior. It states 'validated SAP 10 fuel factors' and notes the tool is a 'precheck', not official. However, it does not describe what happens when multiple parameters are provided, how missing parameters are handled, or any limitations on accuracy or applicability.

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 long, front-loaded with the tool's identity and key actions. Every word serves a purpose, with no redundancy. It is concise and well-structured.

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

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

Given the three parameters and no output schema, the description covers the main purpose and provides some context about fuel factors and official requirements. However, it omits details about the expected output format (e.g., a band string or numeric values), which could be important for agent usage.

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

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

The input schema already has 100% coverage with descriptions, so baseline is 3. The description adds minor context (e.g., fuel types for annual_energy_kwh, returning EPC band for sap_rating) but does not significantly enhance understanding 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 clearly states two functions: mapping SAP rating to EPC band and computing CO2/primary energy from fuel consumption. It also clarifies that the official EPC band requires a full assessment, distinguishing it from the official process. However, it does not explicitly differentiate from sibling tools like calculate_carbon or building_carbon_footprint, which might overlap.

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 is provided on when to use this tool versus alternatives. It does not mention siblings, prerequisites, or exclusions. The 'and/or' phrasing is vague about combining inputs. The description lacks explicit usage 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It lists returned values but does not mention side effects, auth requirements, or computational costs, providing moderate transparency.

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

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

The description is a single, efficient sentence that front-loads the purpose and lists outputs without unnecessary words.

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

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

Given the tool has 7 parameters and no output schema, the description is too brief, lacking details on parameter usage, dependencies, or typical workflows.

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 only 29%, but the description does not elaborate on any parameter meanings, leaving the majority of parameters undocumented.

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 identifies the tool as a thermal load estimator for data centres/critical facilities and lists specific outputs, but does not explicitly differentiate from similar sibling tools like estimate_cooling_load.

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 is provided on when to use this tool versus alternatives, nor are there any exclusions or prerequisites mentioned.

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 description adds caveats about grid factor confidence and base-year, and mentions the legal context. However, it does not disclose behavior around parameter interactions (e.g., both gas inputs), idempotency, or side effects. With no annotations, this is partial coverage.

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

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

The description is a single sentence that packs key information: purpose, scope, geography, legal context, and caveats. It is efficient but could be slightly 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?

With no output schema, the description fails to describe return values, units, or handling of optional gas inputs. For a calculator tool, this leaves significant gaps for the agent.

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 75%, and the description adds context for emirate (emirate-specific factors) and the legal context. However, it does not explain the difference between gas_kwh and gas_m3 or provide additional parameter details beyond 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 clearly states the tool estimates UAE Scope 1+2 GHG emissions from electricity and gas, referencing emirate-specific factors. It is specific about the resource and purpose, though it does not explicitly distinguish from sibling tools like building_carbon_footprint.

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 use for UAE mandatory reporting but provides no explicit when-to-use or when-not-to-use guidance. No alternatives are mentioned, and usage context is only implied.

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

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

With no annotations, the description provides good behavioral disclosure: it returns a verdict and is indicative, signaling no destructive action. It also lists output elements (conditions, flags). Slightly more detail on non-read-only traits would improve, but current is strong.

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, front-loaded with purpose, no redundant words. Every sentence adds value: purpose, output, caveat.

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

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

Given 10 parameters, no output schema, and no annotations, the description adequately covers the tool's domain and key outputs. However, it does not explain all parameters or return format details, leaving moderate gaps for an agent.

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 only 30% (3 of 10 params have descriptions). The description adds context for proposal types and flags (e.g., listed building, Article 4) but does not fully compensate for undocumented parameters like property_type or location specifics. Enums provide some self-documentation.

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

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

Description clearly states it is a UK permitted development rules engine for extensions, loft conversions, and change of use. It specifies the regulation (GPDO 2015, England) and lists typical verdicts and flags, fully distinguishing it from sibling 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?

Description implies usage context (checking PD for specific proposals) and includes a caveat 'Indicative, verify with the LPA'. However, it does not explicitly state when not to use the tool or mention alternatives among siblings.

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