WattGap for Agents

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, so the bar is lower. The description adds the important behavioral boundary that the tool performs screening only and does not produce a final eligibility determination, which is meaningful beyond the annotations. This gives agents a clear sense of the tool's scope and limitations.

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

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

The description is two short sentences with no filler. The first sentence states the core action and input, and the second delivers a crucial caveat. 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?

For a simple one-parameter, read-only tool with annotations and an output schema, the description covers the essential purpose and limitation. It does not mention alternative tools for final determination, but sibling names are provided separately in the context, so an agent could infer where to go next. Overall, the description is nearly complete for its 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?

The schema has a single 'zip' parameter with no description and 0% schema_description_coverage, so the description must compensate. The phrase 'based on ZIP-level facts' clarifies that the zip parameter refers to a geographic zip code and that results are scoped to that level, adding some meaning beyond the name. However, it does not explain the expected format, source of facts, or edge cases, so compensation is partial.

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 that the tool screens potentially claimable programs based on ZIP-level facts, which is a specific action on a specific resource. It also distinguishes the tool from a final eligibility determination, though it does not explicitly name a sibling tool for that purpose. This makes the purpose clear but slightly under-differentiated from siblings like get_program_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?

The phrase 'This is screening only, not a final eligibility determination' implies that this tool should be used for preliminary checks rather than authoritative answers, but it does not explicitly state when to prefer this tool over get_program_status or another sibling. The usage context is implied rather than spelled out.

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

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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds that no household PII is requested, which is a valuable privacy-related behavioral trait beyond what annotations provide.

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. All information is front-loaded: the verb and resource are immediate, followed by key inclusions and a privacy note. No wasted words.

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

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

For a simple tool with one parameter and an output schema, the description adequately covers its purpose, inputs, and privacy aspects. It is sufficient for an agent to understand the tool's core function and safety.

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?

With 0% schema description coverage, the description must compensate. It only mentions 'ZIP-level' indicating the zip parameter, but lacks details like the format or validation pattern (^\d{5}$). Minimal additional semantic value.

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

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

The description clearly states the tool retrieves a ZIP-level home-energy profile, listing key components (utility, rebate potential, provenance). It is distinct from siblings like check_rebates or get_program_status, which focus on specific aspects.

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

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

The description implies use for obtaining a broad energy profile per ZIP code and notes no PII is requested, but does not explicitly state when to use this tool over alternatives or provide exclusion criteria.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds value by explaining it handles cases of unknown coverage, providing behavioral nuance beyond 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?

A single sentence that is front-loaded and concise with no wasted words. Every part contributes to understanding.

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

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

Given a simple single-parameter tool with rich annotations and an output schema, the description is adequate. It covers the key purpose and why to use it, though it could mention the output format or scope more explicitly.

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

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

With 0% schema description coverage, the description should compensate. It only implies 'for a ZIP' without explaining the parameter's format or constraints beyond the schema pattern. The description adds little meaning.

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 'get' and the resource 'program status' with specific attributes (availability, freshness, provenance). It distinguishes from sibling tools like check_rebates by focusing on status and coverage uncertainty.

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 'without guessing when coverage is unknown' provides clear usage context, suggesting this tool is for definitive status when uncertainty exists. However, it does not explicitly mention alternatives or when not to use it.

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

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

Annotations already indicate read-only, open-world, idempotent, non-destructive. The description adds value by mentioning 'provenance and honest confidence', hinting at output metadata. No contradictions.

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

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

Single sentence, front-loaded with verb and resource. No unnecessary words. Highly 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 simple lookup with output schema, the description covers the input and hints at output (provenance, confidence). Could mention invalid ZIP handling, but overall adequate.

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?

With 0% schema description coverage, the description must explain the 'zip' parameter. It only says 'for a ZIP', missing details like required 5-digit format, examples, or validation. Minimal added meaning.

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 resolves the serving electric utility for a ZIP code, with specific verb 'resolve' and resource 'electric utility'. It is distinct from siblings like 'check_rebates' and 'get_energy_profile'.

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

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

Usage context is implied but not explicitly stated. No guidance on when to choose this over sibling tools or when not to use it. The description assumes the user knows to use it for utility lookup.

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