Utilify

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

No annotations provided, so the description carries full burden. It fully discloses that the tool requires a signup_id, returns status (pending, confirmed, failed) plus next-step instructions, and specifies actions for missing ID and long-pending/failed statuses.

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 paragraph that is moderately long but each sentence serves a purpose (purpose, usage examples, edge cases, recommendation). No redundant information; it is well-structured with the main purpose stated first.

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 explains return values (status and next-step instructions). It covers all expected scenarios: missing ID, pending, confirmed, failed, and provides actionable guidance for each. Complete for a status-check 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?

Input schema has 100% coverage for the single parameter 'signup_id' with a description. The tool description adds context about requiring a prior initiate_signup call and handling cases where the user lacks an ID, which adds 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 'Check where a previously-started Utilify signup stands' – a specific verb and resource. It distinguishes itself from sibling tools like initiate_signup and get_provider_details by focusing on checking enrollment status.

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 provides when-to-use with example user queries ('did my electricity signup go through'), when-not-to-use (if no signup_id, tell user no enrollment and offer to start one), and alternatives for edge cases (recommend concierge for pending >48h or failed).

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, description carries full burden. It explains output (structured comparison across price, contract, features, ratings), limitations (TDU filtering), and sequencing dependency. It doesn't explicitly state idempotency or read-only, but the context implies a safe read operation. Still, it's 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 somewhat lengthy but every sentence adds value. It is front-loaded with core purpose. The structure is logical: what, when, how, limitations, sequencing. Could be slightly trimmed, but still 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?

Given only 2 parameters, no output schema, and no annotations, the description covers all necessary aspects: purpose, usage, limitations, sequencing, output nature. It is complete enough 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 has 100% coverage with descriptions for both parameters. The description reinforces the meaning of provider_slugs and address but doesn't add much beyond what the schema already provides. The added context about TDU filtering is helpful but not critical for parameter understanding. Baseline 3 is appropriate.

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

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

Description clearly states the tool compares 2–5 Texas utility providers side by side, with specific verb 'compare' and resource 'providers'. It distinguishes from siblings like search_utility_providers (which surfaces providers) and get_provider_details (single provider). The use case is precise: when user is deciding between specific named options at a new address.

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 when to use ('user says help me pick between these two'), when not to use (across utility types), and provides sequencing guidance (best after search_utility_providers). Also explains that providers not serving the address's TDU will return no plans, setting proper expectations.

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 output format (ordered list of utility tasks with status), conditional logic based on tenancy and rural addresses, and the sequencing recommendation. It could mention whether the tool is read-only, but that is implied.

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 several sentences long but front-loaded with purpose and usage examples. Every sentence adds value, though it could be slightly trimmed without losing 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?

Given 3 parameters, no output schema, and sibling tools, the description is complete. It covers the output, edge cases (rural addresses, different tenancy types), and next steps (search_utility_providers, concierge service). It is self-contained.

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

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

Schema coverage is 100%, so baseline is 3. The description adds significant meaning: it explains that 'tenancy' shapes the checklist and unlocks cross-sells, and that 'move_date' is used for timing. It provides context beyond the schema descriptions.

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

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

The description clearly states the tool generates a personalized move-in utility checklist for a Texas address. It uses specific verb 'generate' and resource 'checklist', and distinguishes from sibling tools like search_utility_providers by positioning itself as the starting 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?

The description provides explicit usage guidance with example queries ('I'm relocating...', 'give me a checklist...'). It also specifies when to mention the concierge service. However, it does not explicitly list cases where the tool should not be used.

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 fully discloses key behaviors: promotions are TDU-aware for electricity, returns active promotions with discount details and expiration dates, and that calling without an address returns a generic list that may include un-buyable offers.

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, starting with purpose, then usage examples, then behavioral details, and finally parameter guidance. It is slightly lengthy but every sentence adds value, and the information is front-loaded.

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

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

Given the tool has no output schema and no annotations, the description covers all essential aspects: what it returns, filtering options, address importance, and the TDU-aware behavior. It is complete for the agent to use correctly.

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

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

Schema coverage is 100%, but the description adds meaning beyond the schema by explaining how filtering with utility_types or provider_slugs narrows results, and emphasizing the importance of passing the address for accurate offers.

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 retrieves current deals, coupons, and exclusive offers for utilities at a Texas address. It gives specific verb-resource combinations ('get current deals') and distinguishes from sibling tools like 'compare_providers' or 'initiate_signup' by focusing solely on promotional offers.

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 scenarios for use, such as when the user asks for the cheapest electricity deal or wants a coupon before signing up. It also advises on calling with or without an address, though it does not explicitly state 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, the description carries the full behavioral burden. It explains that the tool returns 'available plans at the given ZIP with rates, contract length, early-termination fees, and signup requirements' and discloses the impact of omitting zip_code. While it doesn't explicitly state read-only or auth requirements, it implies a safe query operation.

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 at 5 sentences, front-loading purpose, then usage examples, then behavioral details, then exclusions. Every sentence adds necessary 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?

Despite no output schema, the description sufficiently explains what is returned (plans, rates, contract length, fees, signup requirements). It addresses sibling tools and provides complete context 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?

Although schema coverage is 100%, the description adds value beyond the schema by explaining the behavioral effect of zip_code (filtering vs statewide catalog) and advising when to pass it. Provider_slug is adequately described in 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: 'Get plans, pricing, and terms for a specific Texas utility provider'. It specifies the resource (provider plans) and action (get details), and explicitly distinguishes from sibling tools like search_utility_providers and compare_providers.

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 when-to-use guidance: 'use after search_utility_providers has narrowed the list' and gives concrete example user utterances. It also clearly states when not to use: 'Don't use this to discover providers (use search_utility_providers) or to compare across REPs (use compare_providers).'

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

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

Annotations set destructiveHint=true, and description reinforces this by noting enrollment is user-initiated and requires confirmation. Adds caveats about error handling and API enrollment, though does not explicitly mention destructiveness.

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 well-structured with enumerated caveats, but somewhat lengthy. Front-loaded with main purpose and usage, but could be trimmed slightly without losing 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?

Covers return types (signup URL, phone, signup_id), error scenarios (TDU mismatch), and alternatives (concierge, check_signup_status). Adequate given no 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?

Schema provides 100% coverage with descriptions for all 6 parameters. Description adds minor context (provider_id accepts UUID or slug) but mostly restates schema info, so baseline 3 is appropriate.

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

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

Clearly states the tool initiates enrollment with a utility provider at a Texas address, after user confirmation. Uses specific verbs ('Start enrollment') and distinguishes from siblings like check_signup_status.

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 describes when to use (after user chooses plan and confirms, with example phrases) and when not to (TDU mismatch -> search again; concierge request -> point to URL).

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

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

Annotations only have openWorldHint: true, so the description carries the full burden. It discloses that the tool returns a lead ID, confirms next steps, routes to specific installer partners, and that Utilify may earn a referral fee. No contradictions with annotations.

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

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

The description is thorough but slightly verbose; however, it is well-structured with bullet points and caveats, making it easy to digest. It front-loads the core purpose and then lists conditions. A bit long but still 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?

Given the complexity (9 parameters, one required, no output schema), the description covers return values, non-returned behaviors (routing to partners), geographical restrictions, opt-in requirements, and anti-duplication rules. It is complete for an agent to use 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 baseline is 3. The description adds minimal parameter-level detail beyond what's already in the schema (e.g., reiterating that email or phone is required). It effectively relies on the schema to describe 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 states it captures Texas homeowner interest in rooftop solar and routes to an installer. This is a specific verb-resource combination and the sibling tools (check_signup_status, compare_providers, etc.) are distinct, so no confusion.

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 says when to use (homeowner mentions solar, solar quotes, etc.), when not to use (renters, non-Texas), and provides concrete example utterances. Also includes caveats against double-calling and opt-in requirements, giving the agent clear guardrails.

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 details including return format, handling of water results (primaryForZip filter), trash provider metadata, propane/septic presence in urban areas, and TDU-based filtering for electricity. Caveats are numbered and explained.

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 long but well-structured: it starts with purpose, lists types, gives usage examples, then provides parameter guidance and numbered caveats. Every sentence adds value, though a more concise version could eliminate some 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 complexity (3 parameters, no output schema, no annotations), the description is remarkably complete. It covers all major aspects: triggers, parameter effects, return content, regional variations, and edge cases like municipal utilities. Nothing essential is missing.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the implications of tenancy values ('rent' vs 'own') and elaborating on utility types such as propane and septic as rural alternatives, which goes beyond the schema's simple enum 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 the tool finds utility providers for Texas addresses, covering nine specific utility types. It distinguishes from sibling tools by providing example user utterances that trigger this tool, making its 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 explicitly lists when to use the tool with concrete user phrases like 'I'm moving to Houston' and explains how the tenancy parameter affects results. It also implies when not to use it by comparison to sibling tools that handle comparisons and sign-ups.

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