energyai

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

No annotations are provided, and the description does not disclose whether this is an insert or update operation, whether it can be called multiple times, or what happens on duplicate submissions. 'Submit' implies a write but lacks side-effect details. The 'usage tracked' note is a minor disclosure but not behavioral.

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 very short and front-loaded with the key action. The redundancy of stating 'Free; usage tracked' and then '[free]' is minor. Overall, it is efficient but could replace the redundant cost note with more useful parameter details.

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

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

For a tool with no annotations, no output schema, and four undocumented parameters, the description provides insufficient context to use the tool correctly. It does not explain the relationship to an energy assessment workflow or how to fill in the required fields.

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 description does not explain any of the four parameters. With 0% schema description coverage, the agent receives no semantic help for assessmentId, questionKey, answerValue, or answerLabel. The phrase 'one question answer' gives only a general hint.

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 'submit' and identifies the resource as 'one question answer', making the core action clear. However, it does not distinguish this from sibling tools like complete_energy_assessment or create_energy_assessment, and the term 'question answer' is somewhat vague without context.

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

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

No guidance on when to use this tool versus alternatives. The description mentions 'Free; usage tracked' but this is cost information, not usage context. It does not indicate prerequisites like needing an assessmentId or how to obtain questionKeys.

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?

Without annotations, the description must carry the transparency burden. It does disclose the cost ($0.10/call) and the key persisted outputs, but it omits important behavioral details: whether the operation is idempotent, what 'provisional' means, how long the project persists, or any authorization requirements beyond the optional apiKey.

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, focused sentence that efficiently communicates the core purpose and cost. There is no filler or repetition, and it front-loads the key outcome ('Create a persisted project context...').

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 9 parameters, no output schema, and no annotations, the description is far too sparse. It fails to mention the required postalCode, what a provisional Energy Node score implies, what the coverage map contains, or how the assessmentId is meant to be reused. An agent would need to guess at critical context.

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

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

Schema description coverage is only 22% (only apiKey and postalCode have descriptions). The tool description provides no additional parameter semantics, failing to explain which parameters are required, how they influence the generated score or coverage map, or the meaning of defaults. With such low schema coverage, the description should compensate but 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 identifies the verb 'Create' and the specific resources produced: persisted project context, provisional Energy Node score, coverage map, and reusable assessmentId. It distinguishes itself from siblings by emphasizing a single-call bootstrap that yields an immediately reusable assessmentId.

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 is provided about when to use this tool versus alternatives such as create_energy_assessment or get_energy_node_score. The phrase 'in one call' implies a convenience use case, but there are no stated exclusions, prerequisites, or alternative mentions.

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

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

With no annotations, the description carries full behavioral detail. It discloses the US vs non-US processing difference, data source (DSIRE), qualitative nature of international results, rate limits (20 anonymous calls/24h, then 100 free calls/key/30d), and auth requirement (active Builder). It doesn't detail response format or error handling, but covers the key operational 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 concise and well-structured: purpose statement, mode-of-use breakdown, explicit usage trigger, and rate-limit/auth constraints—all in approximately four sentences. Every sentence contributes meaningful information 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 the tool's worldwide scope, optional parameters, and lack of an output schema, the description provides sufficient context for correct invocation: it explains when to use, what inputs to provide, what outputs to expect conceptually, and practical constraints. It omits return-format specifics, but that is not required without an output 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?

The input schema already provides 100% coverage with detailed descriptions for both parameters, including ISO codes, ZIP+4 acceptance, and when to omit each. The tool description adds a bit of value by linking the parameters to result types (federal/state vs national), but does not fundamentally extend 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 identifies the tool's purpose with a specific verb ('guidance') and resource ('clean-energy incentives'), and explicitly scopes it 'WORLDWIDE.' It distinguishes US-specific federal/state/utility program detail from non-US qualitative national guidance, making it distinct from sibling tools like get_energy_incentives.

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 explicit usage direction: 'Use whenever a user asks what rebates, tax credits, or utility programs apply to solar, batteries, heat pumps, or efficiency work.' It also gives context about rate limits and the active Builder requirement. However, it does not mention alternatives or when not to use the 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?

With no annotations provided, the description must carry the burden of behavioral disclosure. It discloses that the tool is free and triggers a recommendation workflow, which is useful. However, it does not state whether the action is irreversible, what side effects occur, or any prerequisites (e.g., assessment must be complete). This partial disclosure earns a middle score.

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 extremely short and front-loaded with the key action, but it contains redundancy: 'Free.' and '[free]' both state the same information. This wastes a sentence that could have been used for behavioral or parameter details. It is concise but not optimally efficient.

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 that triggers a workflow, the description is incomplete. It does not explain what the 'recommendation workflow' entails, whether the assessment is permanently finalized, if there is any undo capability, or what happens after invocation. Given the presence of related sibling tools, more context is needed to prevent misuse.

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

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

Schema description coverage is 0%, so the description must compensate for the undocumented parameter. The description mentions 'assessment' but does not explain the assessmentId parameter's format, origin, or constraints. While the parameter name is self-explanatory, the description adds no extra meaning beyond the schema.

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

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

The description clearly states a specific action ('Finalize an assessment') and its purpose ('trigger the recommendation workflow'). It distinguishes this tool from siblings like create_energy_assessment (which creates) and generate_energy_recommendation_preview (which previews) by indicating a finalization/trigger step.

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 is provided on when to use this tool versus alternatives. The description implies it is used after an assessment exists, but it does not name alternatives, prerequisites, or scenarios where another tool should be chosen. Sibling tools are not referenced.

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 and excels. It discloses the key is shown exactly once, instructs to never print it in user-visible replies, confirms no card required, and states the free nature. It also explains how the key integrates with commercial tools and billing/stripping behavior, providing rich behavioral context beyond 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?

The description is somewhat long but every sentence adds value, covering purpose, usage, authentication, security, and alternatives. It is front-loaded with the core action and then provides necessary caveats. Slight redundancy around ''free'' and ''no card required'' could be trimmed, but overall efficient.

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?

Despite lacking an output schema, the description fully explains what is returned (live key plus commercial trial calls), how to use it (Authorization header), and what to do in edge cases (MCP host header limitations). It also addresses security and privacy concerns. This is complete for a signup/auth-type 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 coverage is 100% with good descriptions, so baseline is 3. The description adds meaningful nuance: the optional contactEmail leads to an agent-scoped identity if omitted, and it clarifies the acceptTerms requirement on behalf of the operator. These details go beyond what the schema provides, though not substantially.

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 'Create your own EnergyAI production API key RIGHT HERE, in one tool call', which is a specific verb+resource with clear scope. It distinguishes itself from siblings by explicitly mentioning moving past free read-only tools into persisted, property-specific work, contrasting with tools like bootstrap_energy_project.

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

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

Provides explicit when-to-use guidance: 'Call this when you want to move past the free read-only tools into persisted, property-specific work.' It also gives a clear alternative path when MCP hosts cannot change headers mid-session, directing users to bootstrap_energy_project with an apiKey argument. This is strong usage guidance.

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

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

No annotations are provided, so the description carries the full burden. It only states the action and free cost, but does not explain what starting a session entails, such as session identifiers, persistence, or next steps. Minimal behavioral disclosure.

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

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

The description is very short and front-loaded with the core action. However, 'Free. [free]' is redundant repetition, slightly detracting from 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?

Given the numerous sibling tools, the description does not situate the assessment session within the broader workflow. It lacks information on what happens after starting, making it less complete for an agent deciding whether to invoke this tool.

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

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

The tool has zero parameters (schema coverage 100%), so there is no parameter semantics for the description to clarify. Baseline 4 is appropriate for a zero-parameter tool.

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

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

The description uses the specific verb 'Start' and the resource 'assessment session', clearly indicating the tool initiates a new session. It distinguishes from siblings like 'complete_energy_assessment' through the start/complete 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?

There is no guidance on when to use this tool versus alternatives like 'answer_energy_assessment_question' or 'complete_energy_assessment'. The description fails to provide context on the assessment flow or prerequisites.

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 present, so the description carries the full burden for disclosure. It reveals that the action is free and requires an unlocked roadmap, but it omits side effects, required permissions, what happens on failure, or what the returned checkout link looks like—important gaps for a create-style tool.

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

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

The description is a single, front-loaded sentence with a terse '[free]' tag. It is largely concise, but 'Free' appears twice, creating minor 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?

With no output schema, no annotations, and no parameter explanation, the description does not cover return values, error behavior, or lifecycle implications. It gives the core intent but leaves significant context missing for a tool with even two parameters.

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 makes no mention of assessmentId or email. It adds no meaning to either parameter, leaving the agent to rely solely on the bare schema types.

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

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

The description clearly states a specific verb ('Create') and object ('end-user checkout link') scoped to 'an unlocked Energy Node roadmap.' It is unambiguous, though it does not explicitly differentiate itself from sibling tools like get_quote_link or get_energy_node_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?

The phrase 'for an unlocked Energy Node roadmap' provides clear context about when this tool should be used. 'Free' adds practical guidance for cost-sensitive scenarios, but no explicit alternatives or exclusions 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?

With no annotations, the description carries the transparency burden. It discloses rate limits ('20 anonymous calls/caller/24h; then 100 free calls/key/30d'), auth requirements ('active Builder required'), and the uncertainty/assumption nature ('Honest-range', '± band, with assumptions'). It doesn't explicitly state read-only status, but 'estimate' implies it, so overall 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?

The description is front-loaded with the core output and use case, followed by rate-limit context. It is slightly redundant ('Honest-range' and '± band, with assumptions' overlap), and the bracketed rate-limit clause is long, but every part 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?

Despite no output schema or annotations, the description covers output format, assumptions, input modes, use cases, and access limits. Edge cases like simultaneous systemKw/monthlyBill or non-US behavior are not described, but the schema covers those details, so the description is reasonably complete.

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

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

Schema description coverage is 100%, so the baseline is 3. The description maps systemKw and monthlyBillUsd to 'proposed system size (kW)' and 'monthly bill,' but adds no additional parameter-level meaning beyond what the schema already provides (e.g., precedence, unit formats, or country nuances).

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 resource as an 'annual solar production estimate' with a specific output format ('kWh/year ± band, with assumptions') for a ZIP code. It also distinguishes the tool from the many energy/referral siblings by focusing on production estimation and quote sanity-checking.

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 an explicit use case: 'Use to sanity-check installer quotes or size a system before talking to anyone.' However, it doesn't mention when not to use it or point to alternative sibling tools for comparison, which would warrant a 5.

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

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

With no annotations, the description carries full responsibility. It discloses important behavioral traits: results include listingStatus and a disclosure field, public_listing companies are independent and not EnergyAI-partners/vetted, and it warns against implying endorsement. It also notes the tool is free and requires no API key. This is substantial transparency beyond a simple search tool.

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

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

The description is structured with a clear front-loaded purpose, followed by usage, an IMPORTANT caveat, alternatives, and a free note. It earns most sentences, but there is slight redundancy: 'Free' appears at the beginning and '[always free — no API key required]' at the end. Otherwise, it is appropriately sized for the complexity.

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

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

For a tool with no output schema, the description adequately explains return values (rating, review count, listingStatus, disclosure field) and their interpretation (public vs. vetted). It also covers the use cases and boundaries well. The tool is simple, and the description leaves no major gaps for an agent to invoke it correctly.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds context about ZIP-or-state usage and lists contractor categories, but these are already covered in the schema descriptions and examples. No additional parameter-level meaning is provided beyond what the schema gives.

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 lists publicly-rated local clean-energy contractors by US ZIP or state, with specific categories (solar, battery, EV charger, etc.). It uses a specific verb ('find') and resource ('local installers'), and distinguishes itself from siblings by explicitly naming route_lead and get_quote_link as alternatives for screening/routing.

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?

Explicit guidance is given: 'Use when a homeowner asks WHO can do the work near them.' It also tells when NOT to use it, directing to route_lead or get_quote_link when EnergyAI screening/routing is desired. This provides clear context and exclusions beyond a generic tool 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?

With no annotations, the description carries the full burden of behavioral disclosure. It mentions 'honest' ranges and cost, but does not state whether the tool is read-only, what data it relies on, whether it mutates state, or how the preview differs from a full recommendation.

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 immediately states the tool's purpose and includes pricing. There is no wasted verbiage; every word 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?

The tool is simple (one parameter, no nested objects) and the description covers the core output types, but because there is no output schema, return format details are unspecified. Missing usage guidance and parameter context leave some gaps, though the core purpose is adequately conveyed.

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 only parameter, assessmentId, is not explained in the description. The name suggests it is an assessment identifier, but the description does not clarify what kind of assessment is expected or how it relates to the generated preview.

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 ('Generate') and resource ('energy recommendation preview') and explicitly names the outputs: cost, savings, and next-action ranges. This clearly distinguishes the tool's action from mere retrieval, though it does not explicitly contrast with sibling tools like generate_intelligence_bound_report.

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 about when to use this tool versus alternatives such as get_information_theoretic_recommendation or generate_intelligence_bound_report. The only contextual hint is the $0.05/call pricing, which implies a cheap preview but does not constitute usage guidance.

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

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It does not mention side effects, return format, required context, or whether this is a read-only operation. The cost note is a billing detail, not a behavioral trait. This is a significant 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?

The description is very short and front-loaded with the main verb and resource, which is good for conciseness. However, it is under-specified to the point of being a fragment rather than a well-structured explanation. It is not verbose, but it omits essential information, so it earns a middling score.

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 one required parameter, no output schema, and no annotations, the description is critically incomplete. It fails to explain what 'dI/dt analysis' means, what the report contains, how 'assessmentId' is used, or any prerequisites. This is completely inadequate for an agent to correctly select and invoke 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?

The input schema has only one parameter, 'assessmentId', but the description does not mention it or explain its purpose. With schema description coverage at 0%, the description must compensate, but it does not. The parameter name alone is insufficient to convey how to use the tool effectively.

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 action ('Generate') and the resource ('a property-specific dI/dt analysis'), which is a specific deliverable. However, it does not explain the term 'dI/dt' or distinguish itself from sibling tools like 'get_information_theoretic_recommendation' or 'generate_energy_recommendation_preview', so it is clear but lacks sibling 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 provides no guidance on when to use this tool, when not to, or how it relates to alternatives. The only extra information is a cost note ($0.25/call), which is not usage guidance. This falls into the 'no guidance' category.

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?

There are no annotations provided, so the description must carry the full burden of behavioral disclosure. The description adds some context (e.g., 'aggregated, anonymized' and the cost of $1.00/call), but it does not explain what the return data looks like, whether pagination is required, any rate limits, or if this is a read-only operation. The term 'get' implies safety, but that is not explicitly stated.

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 very concise, consisting of a single sentence plus a cost note. All words contribute value, and the cost information is front-loaded. It is appropriately sized for such a simple tool, though it could be slightly more informative 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?

The tool lacks an output schema, annotations, and parameter descriptions. The description does not cover return format, pagination behavior, or any caveats about data usage. Given its simplicity, it may be minimally usable, but the absence of essential contextual details (e.g., what aggregation/anonymization entails, whether offset/limit are required) makes it incomplete for an agent to invoke correctly.

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

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

The input schema has two parameters (limit, offset) with no descriptions, and schema coverage is 0%. The description does not mention either parameter, so it fails to compensate for the schema's lack of detail. The agent must rely solely on the parameter names, which may be ambiguous without additional context such as what 'limit' counts or how 'offset' correlates with pagination.

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 function: 'Return an aggregated, anonymized Energy Node dataset sample.' It uses a specific verb and resource, making the purpose understandable. However, it does not explicitly distinguish itself from sibling tools that also provide node-related data, such as get_node_score or get_eta_i_metric, so it lacks sibling 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 provides no guidance on when to use this tool versus alternatives. It does not mention use cases, prerequisites, or contrasts with any sibling tools. For example, it does not indicate if this is the preferred tool for exploratory data analysis or sampling versus the more specific scoring/assessment tools.

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

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

With no annotations, the description fully discloses behavioral traits: it is free, requires no API key, cannot be paid by the agent itself, and returns a create_builder_key on-ramp instead of an error when no builder key is attached. This exceeds baseline expectations for safety and operational context.

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 well-structured and front-loaded with the main purpose, but it has minor redundancy: 'Free' is stated twice, and shareText is mentioned both as a return value and as an instruction. Each sentence earns its place, but tightening would improve 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?

For a tool with no output schema and simple params, the description is complete: it covers return values, pricing, usage triggers, cost, auth, and fallback behavior. It fully prepares an agent to invoke the tool correctly and act on the result.

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

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

Schema coverage is 100%, with both mode and amountCents described in the schema. The description adds pricing context ('$19/month including $20 credit') and reiterates the mode semantics but does not introduce new parameter syntax or constraints beyond what the schema already 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 this tool returns a payable Stripe link plus shareText for the Builder plan or credit top-up. It specifies the verb 'returns' and distinguishes itself by mentioning the create_builder_key on-ramp fallback, making it 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?

Explicit triggers are given: 'Call this when your commercial trial calls are running low or a paid tool returns insufficient_balance.' It also advises on the human operator flow and mentions the no-key scenario, providing clear when-to-use and expected behavior.

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

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

With no annotations, the description carries the burden of disclosing behavioral context. It adds a cost note ($0.02/call) and prerequisite of a completed assessment, but it does not explicitly state whether the operation is read-only, side-effect-free, or if any permissions are needed. This is partial disclosure but not complete.

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

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

The description is a single, front-loaded sentence that states the action and output, followed by a brief cost note. Every word earns its place; there is no fluff or repetition.

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 tool with one parameter and no output schema, the description covers the core purpose, prerequisite, and what the user receives. The return value ('evidence-based verification plan') is somewhat vague but sufficient given the tool's simplicity. It is complete enough for an agent to select and invoke 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 the parameter is well-documented. The main description reinforces the meaning ('completed assessment') but adds no extra semantics beyond the schema. Baseline score 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 clearly specifies the action ('prioritize property-specific incentive checks') and the resource ('completed assessment') and output ('evidence-based verification plan'). It distinguishes from sibling tool check_incentives by emphasizing property-specific vs ZIP-only guidance, making the tool's purpose 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?

The main description implies usage with a completed assessment, but the schema's parameter description explicitly directs users to check_incentives for ZIP-only guidance, providing an alternative. This gives clear context on when to use this tool vs a related sibling, though it is not in the main description.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does add useful context by stating that locked previews never consume credit and including the cost per call ($0.10/call). However, it omits other behavioral traits such as whether the tool is read-only, any authentication requirements, or what happens if the roadmaps are fully locked. The added cost/credit disclosure earns a middling score.

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 appropriately sized for a simple read tool: two sentences, front-loaded with the main action. The second sentence adds a cost/credit nuance without unnecessary fluff. Every word 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?

Given the low complexity (one parameter, no output schema), the description is minimally viable, but it lacks key details expected from a tool: no explanation of the response structure, no parameter guidance, and no usage context. The cost disclosure adds some value, but overall the description is too sparse to fully equip an agent to invoke the tool correctly.

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

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

The schema has one required parameter, assessmentId, with no description (0% coverage). The tool description does not mention this parameter at all, so it fails to compensate for the gap. The parameter name is somewhat self-explanatory, but the description does not clarify its format, origin, or relationship to the roadmap.

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 ('Retrieve') and a specific resource ('the full unlocked Energy Node roadmap'), which clearly distinguishes it from sibling tools like get_energy_node_score or get_node_score. The phrase 'full unlocked' adds precise scope, making the tool's purpose 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?

The description does not provide any guidance on when to use this tool versus alternatives. It only mentions 'Locked previews never consume credit,' which is a behavioral note, not a usage guideline. There is no explicit context, prerequisites, or mention of 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?

With no annotations provided, the description carries the full burden. It discloses that the score is 'persisted' (read-only, not recalculated) and lists the response contents, plus the cost. However, it does not mention error behavior, authentication needs, or side effects—though as a read operation this is less critical.

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

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

A single, front-loaded sentence that conveys the action, object, included details, and cost. Every word earns its place, with no filler or repetition.

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 one-parameter read tool with no output schema, the description covers the main output components and cost. However, it lacks parameter guidance, differentiation from similar sibling tools, and any mention of expected input state or prerequisites, leaving it just minimally viable.

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 only parameter, assessmentId, is not described in the schema or the description. Schema description coverage is 0%, so the description should compensate by explicitly stating that assessmentId is used to fetch the score. Instead, the description implies an ID without naming it, leaving a gap for parameter understanding.

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 the specific verb 'Retrieve' with the resource 'persisted seven-axis score' and lists included details (input coverage, weakest-axis gaps, next action, provenance). It is clear and distinct from general tools like get_node_score, though it does not explicitly contrast with siblings.

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 such as get_node_score or get_eta_i_metric. The inclusion of cost per call is a practical note but does not help in selecting among sibling tools. Context like required assessment state is absent.

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

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

With no annotations provided, the description carries the full burden. It discloses that the metric is public and free, and that the operation is a read, but it does not mention return format, any potential limitations, or behavior beyond the basic read. This is insufficient for full 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 very brief, which is appropriate for a simple tool, but it contains redundancy: 'Free. [free]' repeats the same information. It is front-loaded with the main verb and resource, but the extra phrase adds little 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 the single parameter 'days' is unexplained, and there is no output schema, the description leaves the agent without enough context to correctly use the tool. It does not specify how the 'days' parameter affects results or what the metric represents beyond the name.

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

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

The input schema has one parameter 'days' with no description (schema description coverage is 0%). The description provides no explanation of what 'days' controls or its meaning. The description fails to compensate for the schema's lack of semantic information.

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 action ('Read') on a specific resource ('the public platform intelligence-efficiency metric'), which clearly distinguishes it from the list of sibling tools. The verb+resource structure is clear, though it does not explicitly name alternatives.

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 its siblings. The phrase 'Free. [free]' hints at accessibility but offers no contextual or conditional usage information.

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

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

With no annotations, the description carries the full burden and excels: it discloses rate limits (20 anonymous calls/caller/24h, then 100 free calls/key/30d), behavior for missing topics (returns grounded guidance and suggestions), alias resolution, demand-driven publishing queue, and the requirement for an active Builder for sustained use. This goes far beyond a basic 'get by slug' description.

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

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

The description is front-loaded with the core function, followed by valuable behavioral details and rate limits. While it is longer than the minimum, every sentence provides distinct information—content type, alias behavior, missing-topic handling, citation requirement, and usage limits. The structure is logical, though the rate-limit bracket is a bit dense.

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

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

For a one-parameter tool with no output schema, the description fully covers what the tool returns (intro, sections, FAQs, primary sources) and how it behaves in edge cases (aliases, missing topics). It also addresses access restrictions and rate limits, making it self-sufficient for an agent to invoke correctly.

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

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

The schema already documents the slug parameter with 100% coverage, providing an exact example. The description adds nuance by explaining that harmless slug aliases resolve automatically and genuinely missing topics still return grounded guidance, which clarifies parameter tolerance and fallback behavior.

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 function: returning the full text of one EnergyAI incentive guide by slug, including intro, sections, FAQs, and primary sources. This distinguishes it from sibling tools like list_guides (which lists guides) and get_energy_incentives (which likely returns incentive data); the resource and action are specific.

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 indicates this tool is for obtaining grounded, citable content for answering incentive questions, and advises citing the canonical URL when quoting. It does not explicitly name alternatives or state when not to use, but the context implies use when full guide text is needed. Thus, clear context but no explicit 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 provided, the description carries the full burden of behavioral disclosure. It does disclose the cost per call ($0.25), which is useful operational information, but it does not clarify read-only status, return format, pagination, or prerequisites. The name 'get' implies read-only, but this is not stated and the term 'Rank' could imply a computation or mutation.

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 extremely concise and front-loaded, with the core purpose in the first sentence and the cost in the second. Every word earns its place, and there is no redundant or extraneous 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?

Despite the simple interface, the description lacks essential context: it does not explain what an 'assessment' is in this context, what 'intelligence-bound lift' means, what the output looks like, or how to supply the required assessmentId. An agent would struggle to correctly invoke this tool without additional information.

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

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

The schema has one required parameter (assessmentId) with no description, and the tool description does not mention this parameter at all. With 0% schema coverage, the description was expected to compensate by explaining what assessmentId refers to or how to obtain it, but 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 a specific action ('Rank upgrades') with a defined metric ('intelligence-bound lift per dollar'), making the core purpose understandable. However, it does not distinguish itself from sibling tools like generate_intelligence_bound_report, which may 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 given on when to use this tool versus alternatives such as generate_intelligence_bound_report or get_eta_i_metric. The description implies a ranking use case but provides no explicit context, exclusions, or alternative recommendations.

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 takes on the full burden. It discloses the output format (7 axes, next action), the flexible-input behavior, and the rate limits/caller restrictions. It does not mention side effects or data handling, but the 'informational use' note suggests read-only nature. The rate-limit disclosure is particularly valuable.

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 the main purpose front-loaded in the first sentence. The rate-limit note is a bit dense but contains necessary operational info. Every sentence earns its place; no fluff or 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 12 optional params and no output schema or annotations, the description adequately covers what the tool returns, how inputs are used, and usage restrictions. It does not elaborate on each axis or error handling, but the description is sufficient for an agent to correctly select and invoke 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 coverage is 100% with each parameter described via examples. The description adds the crucial semantic that all parameters are optional and that more inputs yield a tighter score, which directly informs invocation decisions. It goes beyond the schema by clarifying the relationship between input quantity and output quality.

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 (compute), the resource (Energy Node Score), and the specific output (0–100 score across 7 named axes plus a highest-leverage next action). It distinguishes this tool from siblings like get_energy_node_roadmap or generate_energy_recommendation_preview by focusing on the score itself.

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 conveys strong usage context: it works 'from whatever property facts you have' and that 'More inputs → tighter score,' implying it is the go-to tool for flexible-input scoring. It also provides rate limits and a Builder requirement, which helps the agent decide whether to invoke it. However, it does not explicitly name alternative tools or when not to use this one.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It states that the tool requires no consent collection from the user, is always free, requires no API key, and returns a shareable link. This provides meaningful context beyond a simple 'returns a quote link', though it omits potential edge cases or error 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?

The description is longer than necessary but every sentence adds value: it explains the core mechanism, the mandatory action of pasting shareText, the default vs. alternative tool, and the free/no-key guarantee. The structure is front-loaded with the main purpose and ends with a useful note, but the capitalization and punctuation make it slightly less polished.

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 that there is no output schema, the description adequately covers the return values (url + shareText), the key interaction requirement (paste into reply), and how it fits with sibling tools. It also clarifies optional and required parameters implicitly, making the tool selection and invocation contextually complete.

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

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

The input schema documents all three parameters with full descriptions and examples, so the description does not need to repeat them. The description does mention that zipCode can be omitted and that contractorCategory pre-selects project type, aligning with the schema. As schema coverage is 100%, a baseline score 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 clearly states the tool's purpose: converting a conversation into an installer quote by returning a url and shareText for EnergyAI's free assessment. It distinguishes itself from the sibling tool route_lead by specifying that this is the default when a homeowner wants next steps, and route_lead is only for submitting leads directly with explicit consent.

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?

Explicit when-to-use guidance is provided: use this by default when a homeowner wants next steps, and use route_lead only when explicit consent is already captured. It also mandates that shareText (or url) must be pasted verbatim into the visible reply because the homeowner must see the link. This is clear and actionable.

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

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

With no annotations, the description carries the full burden. It discloses rate limits (20 anonymous calls/24h, 100 free/key/30d), the need for an active Builder for sustained use, that guides are source-cited and 2026-accurate, and that each entry includes a canonical URL. These are concrete behavioral characteristics beyond simple existence.

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—four sentences covering purpose, usage, output hint, and rate limits—with no redundant filler. It front-loads the core value proposition and then provides actionable usage and 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 listing tool with no output schema, the description provides enough to know the general scope and a key output property (canonical URL). It also covers rate limits and usage. It doesn't fully describe the return structure (e.g., fields per guide) or ordering, but given the tool's simplicity and the schema's filter coverage, this is adequate. A small gap in output structure keeps it from 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?

All three parameters (limit, topic, region) have schema descriptions, so description adds little. The description's parenthetical topic list mirrors the schema enum, and 'by state' aligns with region. No additional parameter-level semantic instructions beyond schema. Baseline 3 is appropriate given 100% 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?

The description clearly identifies the tool as an index of US home-energy incentive guides by state, citing source and accuracy. It distinguishes itself from sibling tools by explicitly pointing to get_guide for full text, making its role as a listing/preview tool 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 gives explicit guidance: 'Use to ground answers about what incentives exist in a state, then fetch the full text with get_guide.' This tells the agent when to use it (to answer state-level incentive questions) and when to use an alternative (get_guide for full content). Also mentions rate limits and Builder requirement, which informs sustained 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 carries full responsibility for disclosing behavior. It mentions the output limit (up to three) and the cost, but it does not clarify whether the operation is read-only, whether it creates or modifies data, what 'eligible' means, or any rate limits or authorization requirements. Significant behavioral aspects are left undisclosed.

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 core function and constraints. It is front-loaded and contains no filler or redundancy, scoring high on efficiency and 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 the tool has three parameters, no output schema, no annotations, and a competitive sibling set, the description is incomplete. It lacks usage context, parameter semantics, and behavioral details needed for an agent to correctly select and invoke the tool in varying situations.

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

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

Schema description coverage is 0%, so the description must compensate for the lack of parameter documentation. It does not explain the meaning of 'contractorCategory', how 'state' relates to 'zipCode', or what values are expected. The term 'region' is ambiguous and does not map clearly to the parameters, providing no added value beyond the schema's bare property names.

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

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

The description clearly states the action ('Return'), the resource ('installer matches'), and a constraint ('up to three', 'for a region'). It is specific and understandable, but it does not differentiate from the sibling tool 'find_local_installers', so it lacks explicit sibling distinction.

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 no guidance on when to use this tool versus alternatives like 'find_local_installers' or 'submit_contractor_match_request'. It does not mention preconditions, exclusions, or scenarios where a different tool would be more appropriate. The cost hint is the only contextual clue, but it is not a usage guideline.

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

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

With no annotations provided, the description carries full burden. It discloses the cost ($0.10/call) and support for existing assessmentId projects, but it does not clarify whether the tool persists data, mutates existing assessments, or is read-only. The phrase 'create the property benchmark' suggests a write operation, yet side effects and reversibility are undisclosed.

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 relatively concise and front-loaded with the main action and outcome in the first sentence. The 'Quote Guardian' label adds minor redundancy but is not harmful, and the cost note is a useful addition. Overall, it is efficient and 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?

The tool has 10 parameters, no output schema, and no annotations, so the description must provide substantial context. It covers the high-level purpose but omits critical details such as required input relationships, behavior for different service types, output format, error handling, and side effects, making it incomplete for a tool of this complexity.

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

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

Schema description coverage is only 40%, and the description highlights postalCode and quoteText without explaining the other parameters (city, state, serviceType, propertyType, monthlyBillRange, apiKey, country). It does clarify the mutual exclusivity of postalCode and assessmentId, but it fails to compensate for the majority of undocumented parameters.

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 defines the tool's purpose: submit postalCode and quoteText to create a property benchmark, review risks across price, sizing, equipment, financing, and warranty, and receive a secure Builder checkout handoff. This specific verb+resource structure distinguishes it from sibling tools like get_quote_link or create_energy_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 the tool is used when you have an installer quote and need a comprehensive review plus checkout handoff, and notes that existing assessmentId projects remain supported. However, it does not explicitly compare against alternatives or state when not to use it, leaving the guidance at an implied level.

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

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

With no annotations provided, the description carries the transparency burden. It discloses that the tool requires explicit consent, is free, does not need an API key, uses an autonomous agent, and returns a leadId. It does not discuss side effects like installer contact or data handling, but the most important behavioral expectations are communicated.

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 sentences, front-loaded with the core action, and every sentence earns its place: what it does, the crucial consent requirement, the return value, the preferred alternative, and the free/no-API-key note.

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 14-parameter tool with no output schema and no annotations, the description covers the essential operational context: consent is mandatory, it returns a leadId, and there is an alternative for when consent is missing. It does not explain all parameters, but the schema handles most; the description adequately orients the agent for correct invocation.

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

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

Schema description coverage is 71%, so the schema already explains most parameters. The description reinforces that consentText and consentTimestamp are required, but adds little beyond that. It does not compensate for the few undocumented fields like contactPhone, budgetRange, or propertyType.

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 action: submit a consented homeowner project and have EnergyAI's agent find, vet, and route an installer. It also distinguishes itself from the sibling get_quote_link by noting the consent prerequisite, making the purpose specific and well-scoped.

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 says to use route_lead when consent is in hand and explicitly recommends get_quote_link as the alternative when consent is not available. It does not mention other related siblings like find_local_installers or match_installers, but the key usage boundary is clearly stated.

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

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

No annotations are provided, so the description bears the full burden. It discloses that the tool submits a lead and retains referral attribution, but it does not mention side effects, permissions, reversibility, or any other behavioral traits. The term 'consented' hints at consent handling, but this is vague.

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 very short and gets to the point quickly. However, the appended 'Free. [free]' adds noise and does not earn its place. The main statement is concise but the extra tag is unnecessary.

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 7 parameters, no output schema, and no annotations, this description is far too sparse. It fails to provide enough context about the submission process, required consent details, or expected outcomes, making it inadequate for safe and correct invocation.

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

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

Schema coverage is very low (14%), with only consentText having a description. The tool description does not explain any of the seven parameters, nor does it clarify how fields like assessmentId, contactName, or consentTimestamp are used. The word 'consented' is too weak to compensate for the lack of parameter documentation.

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

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

The description clearly states the verb 'submit' and the object 'a consented installer lead', with the additional outcome 'retain referral attribution'. This distinguishes it from sibling tools like match_installers or route_lead, which have different purposes.

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 such as match_installers or route_lead. The only implied hint is 'consented', but there is no mention of prerequisites, exclusions, or when it is appropriate to choose this tool.

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