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

Since no annotations are provided, the description carries the burden of behavioral disclosure. It explains the return format (sorted list with tier and water range) and the filtering behavior of min_tier. It doesn't mention side effects or permissions, but for a ranking tool, this is reasonably transparent.

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

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

The description is concise, with two short paragraphs. The first sentence immediately states the primary purpose, and the rest adds essential detail about output and filtering. No unnecessary 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?

The tool has an output schema (though not shown) and a moderately complex set of parameters. The description explains ranking and filtering but omits the role of input_token and output_tokens parameters. It also doesn't clarify what 'models' refers to (e.g., model IDs or names). Given the low parameter coverage and lack of usage guidance, the description is not fully 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 0%, so the description must explain parameters. It only clarifies min_tier (with allowed values and meaning) but says nothing about models, input_tokens, or output_tokens. Given that input_tokens and output_tokens have defaults and are likely used in the evaluation, leaving them unexplained is a significant gap.

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 ranks candidate models by mid-scenario water use for a workload. It specifies the output (sorted least- to most-thirsty, with tier and water range in mL). It doesn't explicitly differentiate from sibling tools like pick_low_water_model, but the verb 'rank' and resource 'models' are specific enough.

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 states what it does but not when to prefer it over sibling tools. For instance, pick_low_water_model might be for selecting a single model, while this ranks all, but no comparison or exclusion is 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?

With no annotations, the description carries the burden and adds meaningful behavior: it enumerates supported OpenAI/Anthropic usage shapes and explicitly states that reasoning and cached tokens are handled without double counting. It does not discuss failure modes, but the pure estimation nature and output schema reduce that need.

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

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

Two front-loaded sentences: the first states the purpose and positioning, the second enumerates the supported usage shapes. Every sentence earns its place, and the density is acceptable given the complex accepted formats.

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 output schema covers return values, and the usage-shape details are strong. However, the description leaves `model`, `region`, and `include_embodied` to their bare schema titles, and given the sibling list_known_models, model semantics are relevant context that 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 description coverage is 0%, and the description richly documents the nested `usage` shape including prompt_tokens, completion_tokens, and cache fields. However, it adds nothing about the required `model` parameter or optional `region` and `include_embodied`, so parameter semantics are only partially compensated.

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: 'Estimate water (mL) from a real API usage object', and 'the accurate path' distinguishes it from the sibling estimate_water tool. It is not a tautology and clearly identifies the tool's domain.

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 gives clear context: use this tool when you have a real API usage object and want the accurate estimate. It does not explicitly name alternatives or state when-not-to-use, so it stops short of full exclusion 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 behavioral transparency burden. It meaningfully discloses defaults (500 output tokens), the role of reasoning_effort when usage is unknown, provider/region overrides, and the return shape (ranges, summary, assumptions). This goes well beyond the schema, though it does not mention failure modes or how unknown models are handled.

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 a clear purpose sentence and then uses compact, information-dense sentences for parameter usage and return values. No sentence is wasted; every clause contributes to correct invocation or interpretation.

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 10-parameter tool with no annotations and no schema descriptions, the description is quite complete: it covers the main estimation path, key overrides, defaults, and output expectations. The main gap is that the required model parameter is not elaborated, and there is no pointer to sibling list_known_models for discovering valid model identifiers.

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 compensates by explaining prompt, reasoning_effort, provider, region, include_embodied, and token-count behavior. However, it refers to token counts collectively rather than explicitly mapping input_tokens, cached_tokens, output_tokens, and reasoning_tokens, leaving a small but meaningful gap.

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 and resource: 'Estimate the freshwater consumed (mL) by one LLM call.' It clearly states the tool's scope and the main input choices (token counts vs. prompt). This differentiates it from siblings like compare_models and pick_low_water_model, which focus on comparison/recommendation rather than single-call estimation.

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 gives clear context on when to provide token counts versus prompt text, how reasoning_effort models thinking tokens, how provider/region override the default profile, and when to set include_embodied=false. It does not explicitly name sibling alternatives or exclusion criteria, so it stops short of 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?

No annotations are provided, so the description carries the full burden. It discloses that this is a read-only operation (listing), that it only includes known models, and importantly explains that unknown models fall back to a default tier with an assumption. This is meaningful behavioral context that helps the agent understand 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 concise and front-loaded: the first sentence states the core function, the second adds essential context about fallback behavior. Every sentence earns its place, with no wasted words or redundant 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?

Given the tool has no parameters and an output schema exists (which presumably lists the models), the description is complete in explaining what the tool does and the key context about unknown models. It could potentially mention that the output includes the default hosting or that it's a read-only call, but these are minor gaps; the output schema likely covers return details.

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

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

The tool has 0 parameters, and the schema coverage is 100% (there are no properties), so the description does not need to explain parameters. The baseline for 0 params is 4, and the description adds no param info, which is appropriate since there's nothing to explain.

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 models with size tier and default hosting, which is a specific verb and resource. It does not explicitly distinguish from siblings like compare_models or pick_low_water_model, but the purpose is clear enough that an agent would understand it's a listing operation, not a comparison or selection.

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

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

The description implies when to use this tool (when you need the list of known models with their defaults) but does not provide explicit when-not or alternative suggestions. It does add context that unknown models work everywhere, which helps an agent decide if listing known models is necessary, but it doesn't reference sibling tools for different needs.

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

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

No annotations provided, so the description carries the burden. It states the tool returns the lowest-water model meeting min_tier and the savings vs. the thirstiest candidate Pdf. It does not disclose behavior when no candidate meets min_tier, nor the meaning of null min_tier. It doesn't mention any side effects (likely none), but could be more explicit about input/output token parameters' role in water estimation. The description is reasonably transparent but has gaps.

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

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

The description is two sentences, front-loaded with the core purpose, then usage guidance. Every sentence adds value with no redundancy.

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

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

With an output schema present, the description need not explain return values, but it does mention what it returns. It covers purpose, usage context, and key parameter guidance. It lacks edge-case behavior (e.g., no candidate meets the floor) but overall is fairly complete for a selection tool with a simple contract.

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 0%, so the description must explain parameters. It explains min_tier (capability floor) and implies candidates. It does not explain input_tokens or output_tokens, which are likely important for water estimation. Partial compensation for two of four parameters, so a 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 opens with a clear, specific statement: 'Pick the least-thirsty candidate model that meets a capability floor.' This precisely identifies the action (pick), the resource (candidate models), and the qualifying condition (capability floor). It effectively distinguishes the tool from siblings like compare_models or estimate_water, which focus on estimation or comparison rather than selection.

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 'Use in agent graphs to route each step' and explains how to set min_tier, giving clear context for when to use it. It doesn't explicitly exclude alternatives or mention when not to use it, but the purpose is clear and aligns with its siblings. A small gap: it doesn't explicitly name sibling tools as alternatives, but the context implies it.

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