WattGap for Agents

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

Annotations already cover the read-only, idempotent, non-destructive and open-world profile, so the description's job is the data-quality story — and it delivers: source URLs, verification dates, explicit unverified status, headline exclusions, separate conditional-income totals, and the caveat that income is unknown and conditional amounts merely illustrate the below-80% AMI tier. This is substantive context an agent cannot get from the annotations, though it omits any mention of rate limits, cost, or caching.

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?

Five dense sentences, none of which is padding — each discloses a distinct output or data-provenance property. Readability suffers somewhat from compressed jargon ('up-to flags', 'sourced financing'), and the most decision-relevant caveat (screening only, not final eligibility) is buried at the end rather than 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?

With an output schema present and a single simple parameter, the description is close to sufficient: it explains what the response excludes and how conditional amounts should be read, which the output schema alone likely cannot convey as intent. The only real gap is the absence of any routing information relative to the sibling tools in this workspace.

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?

One parameter with 0% schema description coverage; the schema only enforces the 5-digit pattern. 'ZIP-level programs' implies the zip scopes results to a single ZIP, but the description adds no detail on accepted formats, whether surrounding ZIPs are included, or what an invalid/missing ZIP yields.

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

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

The description opens with a specific verb+resource ('Screen ZIP-level programs') and closes with a clear scope boundary: 'screening only, not a final eligibility determination.' It does not mention any of the sibling tools (get_program_status, resolve_utility, get_energy_profile), so an agent gets no explicit differentiation among them.

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

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

Usage is implied rather than stated: the 'screening only, not a final eligibility determination' line tells the agent when the output is and isn't sufficient for a decision. There is no explicit when-to-use versus the three siblings, and no prerequisites (e.g., whether resolve_utility or get_energy_profile should run first) are given.

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

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: the headline excludes loans, income-restricted amounts, and unverified rows, conditional income and financing totals are reported separately, no income is inferred from ZIP, and no household PII is requested. What it omits is any note on freshness, coverage gaps for ZIPs with no data, or rate limits.

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?

Four short sentences, front-loaded with the core purpose before the exclusion and privacy details. The caveats about conditional income and no income being inferred from ZIP overlap slightly, but no sentence is filler.

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

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

An output schema exists, so return structure need not be described, and annotations carry the safety profile. Given a single-parameter, read-only lookup, the description supplies everything material an agent needs: what is included in the headline, what is reported separately, and the privacy stance.

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% for the single required parameter, so the description must carry the meaning. It does imply the input is a ZIP and clarifies that no income is inferred from it, but it never states the expected format or validation (the 5-digit pattern lives only in the schema). That partial compensation warrants a mid-range score rather than a full one.

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

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

The description states a specific verb and resource ('Get a ZIP-level energy profile') and specifies what the result contains ('utility and up to incentive screening totals'). It does not name or contrast with the siblings check_rebates, get_program_status, or resolve_utility, so an agent must infer the boundary from the resource names alone.

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

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

There is no explicit when-to-use, when-not-to-use, or prerequisite guidance. The description never mentions when an agent should call this instead of check_rebates or resolve_utility, nor whether a utility must be resolved first, so the selection decision is left entirely to inference from the tool name.

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 the tool as read-only, idempotent, open-world, and non-destructive. The description adds that it reports availability, freshness, and provenance, especially when coverage is unknown, but it does not add further behavioral details such as rate limits, authentication needs, or return format.

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

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

The description is a single tight sentence with the verb and resource front-loaded. Every phrase contributes to purpose or usage context, with no wasted text.

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 one-parameter read-only tool with annotations and an output schema, the description is nearly complete. It explains what is returned at a high level, though it could be slightly fuller on when to choose this over sibling tools.

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 carries more burden for the single required parameter. It identifies the parameter as a ZIP code, but it does not clarify the 5-digit format or other ZIP-specific semantics beyond what the schema pattern already enforces.

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

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

The description uses a specific verb and resource: getting program availability, freshness, and provenance for a ZIP. It is clear what the tool does, but it does not explicitly distinguish itself from siblings such as check_rebates or 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?

The phrase 'without guessing when coverage is unknown' implies a use case for checking coverage gaps, but the description does not explicitly say when to use this versus the sibling tools. Usage is implied rather than directly 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?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The phrase 'with provenance and honest confidence' adds a genuine behavioral signal — results may be uncertain and are attributed — but it is never unpacked (what confidence scale, what provenance source, what happens on ambiguity).

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

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

A single front-loaded sentence with the verb and resource first and no filler. The trailing clause is informative rather than padding, though it is compressed to the point of ambiguity.

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 an output schema present and rich annotations, the description need not explain return values, and one required parameter is trivially discoverable. The main gap is the unaddressed real-world case of a ZIP served by multiple utilities, plus the meaning of 'provenance' and 'confidence'.

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 carry the parameter's meaning; it confirms the parameter is a ZIP serving as the lookup key, but the format constraint (^\d{5}$) lives only in the schema and no semantics are added about which ZIP universe is valid. Adequate minimum, no more.

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

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

States a specific verb ('resolve') and a specific resource ('the serving electric utility') scoped to a ZIP. This is clearly distinct from the sibling tools (rebates, energy profile, program status), though the description never names them to reinforce the boundary.

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

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

There is no explicit when-to-use, no when-not-to-use, and no mention of the sibling tools that could be confused with it. The only guidance is implicit in the purpose statement, and no prerequisites (e.g., US-only ZIPs, what to do when a ZIP spans multiple utilities) are stated.

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