Aguasto Engineering Calculators

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the pure-calculation, side-effect-free nature is established. The description adds the meaningful caveat that results are 'illustrative' and not a measurement or quote, but says nothing about precision, rounding, or what the cost figure is scoped to (per hour vs. per period).

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 short sentences with the computation front-loaded and the scope disclaimer second; nothing is padded. The second sentence is slightly cryptic in isolation but earns its place as an accuracy caveat.

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 four-parameter arithmetic tool with no output schema, the description names the returned quantities, which is the most important missing piece. Still absent is any statement of how the returned values relate to the inputs (e.g. whether cost covers the given hours) or the units/rounding of the output, so the agent cannot fully predict the response.

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 all four required parameters, so the description must carry the load. It only obliquely gestures at the inputs through output concepts ('PUE-adjusted', 'kW', 'kWh', 'electricity cost'), leaving it to the agent to infer that it_kw, pue, hours and usd_per_kwh are the raw inputs and how hours maps to the kWh total.

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 ('Calculate') and specific outputs (PUE-adjusted facility kW, kWh, illustrative electricity cost), so the agent knows exactly what computation is performed. It does not explicitly differentiate from the calculator siblings token_cost and weight_memory, but their domains are clearly distinct.

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 clause 'No facility measurement or commercial quote' implicitly scopes usage to illustrative modeling rather than measured or contractual figures, which is useful. However, it never states when to prefer this over token_cost or weight_memory, nor any prerequisites for the inputs beyond what the schema enforces.

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, non-destructive, closed-world, so the safety profile is covered. The description adds the meaningful caveat that the figure is illustrative and not official Aguasto pricing, which an agent cannot infer from annotations. It says nothing about the response shape, though for a pure calculation tool that is a minor 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?

A single compact sentence with the calculation front-loaded and the caveat trailing, which is the right order. Every clause carries information, though 'illustrative' and the Aguasto disclaimer overlap somewhat.

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 two-parameter, closed-world calculation with no output schema, the description covers purpose and the pricing caveat but leaves the exact formula and parameter units to inference. Adequate but with a notable ambiguity an agent could resolve incorrectly.

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 meaning of both parameters, and it does name them in plain language: supplied cost and completed token count. It also implies normalization to per-million tokens. It does not clarify units, such as whether cost_usd is a total or a per-token rate, nor whether completed_tokens is a raw count, leaving a real ambiguity for a math 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?

States a specific verb and resource: calculate USD per million completed tokens from cost and token count. The computation is unambiguous enough that an agent knows exactly what it gets back. It stops short of a 5 only because 'illustrative' and the Aguasto caveat slightly blur the core statement.

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 'not Aguasto pricing' clause implies when not to rely on the result, which is useful disambiguation. However there is no explicit statement of when to call this versus doing the arithmetic yourself, and no prerequisites 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?

Annotations already declare readOnlyHint, idempotentHint and non-destructive behaviour, so the description only needs to add calculation-scope context — and it does, explicitly excluding KV cache, activations and runtime overhead. That scoping detail is the most valuable part of the definition. It stops short of stating the formula or precision, keeping it below a 5.

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 dense sentence with zero filler; units and exclusions are front-loaded and every clause 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 two-parameter pure calculation with no output schema and strong annotations, the description covers scope, units and exclusions adequately, and 'in decimal GB and binary GiB' hints at the return shape. Only the meaning of the bits parameter is left unaddressed.

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 the burden of explaining the two parameters, and it explains neither. 'parameters_billions' is self-descriptive, but 'bits' (a quantization width enum of 4/8/16/32) is only explained by the schema enum, with no mention of what it represents or how it affects the result.

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 ('Estimate') and resource ('model weight memory') and pins down the units (decimal GB and binary GiB), so an agent knows exactly what the tool computes. It does not name or differentiate from siblings, but facility_energy and token_cost are clearly unrelated calculators, so the gap is minor.

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 only implied: the description establishes the calculation but never says when to reach for this tool versus token_cost or facility_energy, nor does it state any prerequisites. For a simple calculator the implied context is probably enough, but nothing explicit is offered.

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