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

With no annotations, the description carries the full burden; it discloses the defaulting behavior (mirrors interactive calculator), confirms all parameters optional, and enumerates the response contents (result, formula, interpretation, cite_as sentence). It does not discuss edge cases or errors, but for a pure calculation tool this is meaningful transparency.

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?

Three short sentences; the definition is front-loaded, the default/use guidance sits in the middle, and the output contract ends it. There is no 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?

The tool has only four fully documented optional numeric parameters and no output schema. The description fills the output gap by naming the four response pieces, and the calculator link anchors expected behavior. It could have spelled out the formula or units explicitly, but those are already implied by parameter descriptions and the response 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 description coverage is 100%: each parameter already has type, semantics, and a default value. The description adds that all are optional and that defaults come from the linked calculator, but it does not add per-parameter meaning, so the 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?

The description names the exact resource ('fully-loaded cost of one AI agent-hour'), defines its components (compute plus human verification), and frames the comparator (vs the human hour it replaces). It is not a tautology, but it never uses an imperative verb and does not explicitly differentiate from the sibling cost/energy tools, so it stops one step short of a 5.

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?

It says all parameters are optional and defaults mirror the online calculator, which is actionable invocation guidance, and the 'vs the human hour it replaces' clause implies the intended use case. However, it does not specify when to prefer this over sibling tools like token_cost or llm_energy, nor any exclusions, so the usage guidance is implied rather than explicit.

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 all parameters are optional, that defaults mirror an interactive calculator, and that the response includes result, formula, interpretation, and a cite_as sentence. This gives agents a solid understanding of behavior and response contents.

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 compact and front-loaded with the core purpose. Every sentence contributes useful information: the questions answered, the default behavior, the reference calculator, and the response contents.

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 description covers purpose, defaults, response contents, and provides a reference link. It is sufficient for a low-risk optional-parameter calculator, though it could be stronger if it distinguished this tool from closely related siblings like token_cost.

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 schema already documents every parameter and default. The description reaffirms that all parameters are optional and points to the calculator defaults, but it adds little 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 what the tool computes: token count, whether content fits the window, and per-request cost. It frames the purpose as concrete questions rather than a tautology, though it does not explicitly differentiate itself from sibling cost/token tools.

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 opening questions provide clear context for when to use the tool. It does not name alternatives or state exclusions, but the intended use case is evident from the questions and parameter descriptions.

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 carries the disclosure burden and mostly meets it: it reveals the calculation decomposition, that all parameters are optional with defaults, and that the response includes result, formula, interpretation, and a cite_as sentence. It does not enumerate edge cases or failure modes, but for a read-only calculator this 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?

The description is front-loaded with purpose and each sentence earns its place: the question, the energy split model, the defaults/URL, and the response contents. It is slightly longer than strictly necessary but remains well structured with no 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?

For a self-contained calculator with all-optional parameters and full schema coverage, the main missing context is return structure, and the description explicitly supplies result, formula, interpretation, and cite_as. An example would improve it, but nothing essential is absent for a competent agent to invoke it 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?

The input schema already documents all five parameters with units and defaults, so the baseline is 3. The description adds the conceptual grouping 'actuation, inference and idle,' which helps interpret actuation_w, compute_w, and idle_w, but it does not elaborate on individual parameter 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 opens with the exact question it answers ('How long can a humanoid robot run per charge?') and names the resource: humanoid battery runtime split across actuation, inference, and idle. No sibling tool targets humanoid robot runtime, so it is unambiguously distinct despite the shared energy/cost family.

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 a clear use context: estimating humanoid robot runtime from battery capacity and a three-way power split. It does not explicitly name alternatives or when-not-to-use scenarios, but the humanoid-specific framing makes the boundary to token/LLM energy tools obvious.

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 clearly discloses the calculation formula, optional parameters with defaults mirroring an interactive calculator, and the response contents including result, formula, interpretation, and a cite_as sentence. It does not mention edge cases like zero pass rate, but the core behavior is 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 compact and every sentence earns its place: purpose, formula and insight, defaults/source, and response contents. There is no filler, and the important formula is front-loaded immediately after the purpose statement.

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 stateless calculator with six optional parameters and no output schema, the description sufficiently explains what the tool computes, what the inputs default to, and what the response will contain. The only minor gap is the lack of explicit guidance on how model A and model B should be ordered, but the schema names make that reasonably clear.

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 value by explaining how the parameters combine in the formula and what the result means. It also clarifies that all six parameters have defaults, giving operational meaning beyond the individual property 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 names a specific metric (joules per verified task), gives the formula E = tokens × J/token ÷ pass rate, and frames the tool as a model comparison for energy efficiency. It is clearly distinct from energy-only sibling tools because it divides by pass rate, though it lacks a direct imperative verb like 'calculate' or 'compare'.

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 comparing energy efficiency per verified task and states that all parameters are optional with defaults, which tells the agent it can call with zero arguments. However, it does not explicitly name when to choose this tool versus alternatives such as llm_energy or verification_bottleneck, so usage routing is inferred rather than explicit.

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 transparency burden. It discloses that the response includes 'result, formula, interpretation and a ready-to-quote cite_as sentence,' and clarifies default behavior. It does not reveal the actual formula or assumptions, but for a simple calculator tool this is solid behavioral disclosure.

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 three concise sentences: purpose, parameter/default behavior, and output shape. It is front-loaded and contains no filler or redundant restatement. Every sentence 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 calculator with fully documented parameters, the description covers purpose, optional invocation, default source, and response structure. The main omissions are explicit sibling differentiation and more detail about the 'real-world equivalents,' but the definition is complete enough for an agent to invoke the tool 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%, and every parameter already has a description and default value. The description adds only the general note that all parameters are optional and defaults mirror the calculator, which is modest extra value. With the schema doing the heavy lifting, the baseline score of 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 clearly identifies the tool as an electricity/cost/CO₂ calculator for AI queries, with the specific conversion 'Tokens → Wh, joules, dollars, CO₂ and real-world equivalents.' The purpose is immediately understandable and distinct from pure cost tools in spirit. However, it does not explicitly distinguish itself from sibling tools like token_cost, so it falls just short of a 5.

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 says all parameters are optional and defaults mirror the interactive calculator, which is useful invocation guidance. But it provides no explicit when-to-use guidance or alternatives, and none of the sibling tools are mentioned. An agent must infer when llm_energy is the right choice versus token_cost or model_routing.

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 carries the behavioral disclosure burden. It does well by stating that all parameters are optional, defaults mirror an existing calculator, and the response includes result, formula, interpretation, and a cite_as sentence. It does not explicitly say the operation is read-only or side-effect-free, but the calculator framing strongly implies it.

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 compact, information-dense sentences contain the purpose, scope, default behavior, and response composition without repetition. The key question is front-loaded, and every clause contributes useful information.

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 three optional numeric parameters and no output schema, the description adequately explains what the tool returns: result, formula, interpretation, and a cite_as sentence. It could be slightly stronger with an explicit output format or an example, but nothing essential for correct invocation 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 100%, so the schema already documents ratio, share, and spend with units and defaults. The description adds the context that all parameters are optional and that defaults match the interactive calculator, but it provides no additional parameter-level semantics.

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 identifies the tool as a calculator for monthly and yearly savings from routing workload to a cheaper model tier, naming the core resource and computation. It stops short of a direct imperative verb like 'calculate' and does not explicitly distinguish itself from sibling cost-related tools.

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 guidance on when to choose this tool over alternatives such as token_cost or token_burn. The description only implies its use for model-routing savings questions and notes defaults mirror an interactive calculator, but it never states conditions or exclusions.

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 burden, and it does well by disclosing the formula, optional inputs with defaults, and the response structure including result, formula, interpretation, and cite_as sentence. It does not explicitly state that the operation is side-effect-free, but the calculation-oriented nature makes that reasonably clear.

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 tightly written with no filler: a defining question, the formula, the returned outputs, and parameter defaults are all covered in four efficient sentences. Every sentence 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?

Although there is no output schema, the description lists the key response components and the defaults, so an agent can anticipate the result shape. Minor gaps remain: there is no explicit valid range for percentage inputs, and 'claimed autonomy' is not explicitly tied to a parameter, but the formula and defaults make those reasonably inferable.

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%, providing a baseline of 3. The description adds meaning beyond the schema by mapping a, c, r, and t into the PAA formula components P(A), P(C|A), P(R|A,C), and P(T|A,C,R), and clarifies that inputs are percentages with optional values.

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 exactly what the tool computes with a named metric, a precise formula, and an explicit list of returned values (honest percentage, gap, single gate). It does not explicitly differentiate PAA from sibling tools like proof_debt or verification_bottleneck, but the formula and resource are specific enough to establish clear purpose.

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 guidance on when to use this tool versus related siblings such as proof_debt, verification_bottleneck, or token_burn. The description only mentions that all parameters are optional and that defaults mirror an interactive calculator, leaving tool selection entirely to inference.

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 carries the full behavioral burden. It discloses that all parameters are optional, that defaults mirror an interactive calculator, and that the response contains result, formula, interpretation, and a cite_as sentence. This goes well beyond a bare operation statement and gives a clear picture of what the tool returns.

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 with the core purpose, followed by parameter guidance and response contents. The opening label 'Proof Debt Accumulator:' is slightly redundant with the tool name, but each sentence earns its place and there is minimal 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?

For a 7-parameter optional calculator with no output schema and no annotations, the description is well-rounded: it gives scope, defaults, and the response structure. It could be slightly more complete by noting the calculation is read-only or by giving an example, but the core invocation context is sufficiently covered.

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%, with each of the 7 numeric parameters already documented with its default value. The description adds a useful aggregate fact — all parameters are optional and defaults mirror the online calculator — but does not explain individual parameter meanings beyond the schema, so the baseline of 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 clearly states the tool computes the cost of unverified AI work over time, naming backlog, deferred-review premium, and incident liability. This is a specific calculation purpose, though it does not explicitly distinguish the tool from sibling metrics like verification_bottleneck or proof_adjusted_autonomy.

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 framing 'What does unverified AI work cost over time?' implies when to use the tool, and the note that all parameters are optional gives practical guidance. However, it never addresses when to prefer this tool over the related sibling tools, nor mentions any exclusions or prerequisites.

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 disclosure burden. It discloses that all parameters are optional, that defaults mirror an external calculator, and exactly what the response contains (result, formula, interpretation, cite_as). It does not mention side effects, but this is clearly a read/compute 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 three sentences with no filler: it opens with the purpose, states the return values, and notes the defaults and response contents. Every sentence contributes useful information.

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 six optional parameters, no annotations, and no output schema, the description is nearly complete: it names all major outputs and gives the default behavior. It could be slightly richer with an example or a note on how the grade is calculated, but the schema already details parameters.

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 parameters are already well documented with defaults and allowed values. The description adds only the fact that all parameters are optional, which is already visible from the schema, so a 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?

The description clearly explains what the tool computes—revocation exposure across gateways, caches and workers—and names concrete outputs (worst-case window, A–F grade, weakest enforcement point). It does not explicitly contrast it with siblings such as token_burn, so it stops short of full differentiation.

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?

No guidance is given about when to choose this tool rather than related tools like token_burn or verification_bottleneck. The intended use is only implied by the question in the first sentence, with no alternative conditions or exclusions.

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 behavioral disclosure burden. It discloses the response contents: 'result, formula, interpretation and a ready-to-quote cite_as sentence,' and clarifies that all parameters are optional with defaults. This gives meaningful insight into behavior beyond the schema, though it does not detail the underlying formula, assumptions, or potential output format specifics.

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?

Three sentences with no filler. The first sentence front-loads the core output units and scope, the second covers optionality/defaults, and the third describes the response shape. The URL is long but relevant as a source for defaults. Overall compact and well structured.

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?

There is no output schema, so the description appropriately names the response components: result, formula, interpretation, and cite_as sentence. It also states the periods and units (per day and per year; money, kWh, CO₂, households). A minor gap is the lack of explicit relationship to sibling tools and the exact formula/assumptions, but for a simple calculator with fully documented parameters, the description is largely 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 100%, so the schema already documents each parameter and its default. The description adds the high-level guarantee that 'All parameters optional' and that defaults mirror an external calculator, which helps an agent safely invoke the tool with zero parameters. This goes slightly beyond the schema by clarifying optionality and the default-source behavior.

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 function: 'Org-wide token burn as money, kilowatt-hours, CO₂ and households powered — per day and per year.' This identifies the resource and output units, making the purpose understandable. It does not explicitly differentiate from sibling tools like token_cost or llm_energy, but the multi-unit energy/cost scope is distinctive enough to prevent major 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?

The description says 'All parameters optional — defaults mirror the interactive calculator,' which is useful invocation guidance, but it does not state when to use this tool versus alternative siblings such as token_cost or llm_energy. No exclusions, prerequisites, or use-case context are provided, so the agent must infer when this is the right choice.

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 carries the full behavioral disclosure burden, and it does well. It explains that costs are computed with input/output priced separately and a prompt-cache discount, that defaults mirror an interactive calculator, and that the response includes 'result, formula, interpretation and a ready-to-quote cite_as sentence.' This gives an agent a solid model of what will happen and what will be returned. It does not mention rate limits or edge cases, but for a stateless calculator those are less critical.

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 purpose question, followed by pricing details, output format, parameter guidance, and response contents in just a few sentences. The URL and cite_as mention are useful and do not feel extraneous. Every sentence earns its place, and the structure moves from high-level purpose to operational 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?

For a simple calculator with three optional parameters and no output schema, this description is complete. It covers what the tool computes, the pricing logic, default parameter behavior, the ranked output, and the response structure. An agent has enough information to call it correctly and to interpret the result without additional context.

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 input schema already documents all three parameters with units and default values, and schema description coverage is 100%, so the baseline is 3. The description adds the useful fact that all parameters are optional and that defaults mirror the interactive calculator, but it does not substantially deepen meaning beyond the schema. The prompt-cache discount behavior mentioned in the description does add context for the 'cache' parameter, but not enough to push the score higher.

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 question: 'What does a monthly token volume cost across GPT, Claude, Gemini and DeepSeek?' and states concrete behaviors: separate input/output pricing, prompt-cache discount, and a ranked bill per model. This clearly distinguishes the tool from siblings like token_burn, which appears related but is not described. The verb 'returns' plus the resource 'ranked bill per model' makes the tool's function 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 gives a clear use case: computing monthly token costs across major model families, with input/output and cache considerations. It also notes that 'all parameters optional — defaults mirror the interactive calculator,' which tells an agent when no arguments need to be supplied. It does not explicitly name sibling alternatives or state when not to use them, but the scenario is clear enough for correct selection.

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 carries the behavioral disclosure burden. It goes beyond the schema by stating that all parameters are optional, that defaults mirror the interactive calculator at a specific URL, and that the response includes 'result, formula, interpretation and a ready-to-quote cite_as sentence.' This gives an agent useful expectations about calls and outputs.

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 three tightly worded sentences with no filler. It front-loads the core concept and computation, then covers defaults and output structure. Every sentence adds necessary information.

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 numeric calculator with six optional parameters, the description is nearly complete: it states the computation, gives defaults, references the source calculator, and describes the response contents. It does not discuss edge cases or constraints, but the schema already captures units and defaults, and the output is summarized sufficiently in the absence of an 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 coverage is 100%, with each parameter already documented by name, type, default, and units. The description adds that all parameters are optional but otherwise does not add meaning beyond the schema, so the baseline score of 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 'Agents generate in parallel, humans review in series' and then specifies the exact computation: 'the real agent-fleet ceiling from review capacity, minutes per task and rework rate'. This is a specific verb plus resource, making the tool's purpose unmistakable even among the sibling calculator-style tools.

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 by identifying the bottleneck scenario and the computed output, so an agent can infer when this tool applies. It does not explicitly name alternative tools or exclusion criteria, but the intended use case is clear enough without that.

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