Rahul D Sarker: Marketing & RevOps Tools

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds the scoring model (five weighted checks summed to a 0-100 verdict), which is useful context, but adds nothing about limitations, required input quality, or how partial answers are treated.

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 sentences, front-loaded with the purpose and check breakdown. The trailing promotional URL is the only element that does not earn its place for an invoking agent.

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 values need not be explained, and the description covers all five scored dimensions. The only gap is the optional currency parameter and the absence of any routing guidance among similar 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 100% and the five required enums carry their own weights, so the schema does the heavy lifting. The description's list of checks roughly mirrors the parameters but adds no extra semantics (e.g., weighting rationale or handling of "partial"), so the baseline 3 applies.

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 gives a specific verb and resource ("Score a hero section's five-second clarity") and enumerates the five weighted checks, so the agent knows exactly what it produces (a 0-100 verdict). It is clear on its own, but never distinguishes itself from close siblings like value_prop_strength_grader or landing_page_vs_ad_match_quality_auditor, so it falls 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?

There is no guidance on when to use this versus alternatives. With many overlapping copy/landing-page graders in the sibling list, an agent gets no signal about which one applies to a given request.

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 a pure read-only, idempotent, non-destructive, closed-world computation, so the safety profile is fully covered. The description adds the exact statistical method (two-proportion z-test), which is genuinely useful behavioral context, but says nothing about edge cases such as zero visitors or low sample sizes.

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?

Front-loaded with the core purpose in one tight sentence; the follow-on link is short but is promotional rather than agent-relevant, so it does not fully earn 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 stateless calculator with complete annotations, a 100%-covered schema, and an output schema that covers return values, the description is sufficient. Only minor behavioral caveats (input validity or sample-size assumptions) are absent.

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 clear per-parameter descriptions, so the schema carries the parameter burden. The description adds no extra meaning about the required counts or the optional currency field, making the baseline 3 correct.

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 (Run) and resource (two-proportion z-test on an A/B test) and names the outputs (relative uplift, statistical confidence), so the agent knows exactly what computation this performs. No sibling tool duplicates an A/B significance test, so it is 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 usage scenario is implied: this applies when you have A/B visitors/conversions and want significance. However, the description gives no explicit when-to-use, when-not-to-use, or alternative referral 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds nothing behavioral beyond that (no return format, no bounds on inputs, no rounding or currency behavior), which is acceptable for a pure calculator but not additive.

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 first sentence is well front-loaded and efficient, but the second sentence is a promotional link to an external page that gives an agent no usable information, so half the description does not earn 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?

An output schema exists and annotations cover the safety profile, so return values and side effects need not be explained. For a low-complexity read-only calculator with a fully described 5-parameter schema, the only real omission is any usage routing against the many sibling calculators.

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 every parameter including the optional currency pattern is already documented in the schema. The phrase 'SMB versus enterprise segments' loosely maps to the two segment pairs, but adds no syntax, units, or defaulting detail 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?

States a specific verb and resource: 'Break ARR down by SMB versus enterprise segments' and clarifies the output intent (revenue concentration, per-customer averages). This is clear enough to separate it from generic ARR tools like mrr_to_arr_calculator or arr_multiple_calculator, but it never names a sibling to route against.

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 when-to-use guidance, no prerequisites, and no mention of when a different ARR/segment calculator would be the better pick. The description only says what the tool computes, leaving 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered and the description rightly does not repeat it. It adds the output content (days-to-fatigue and a creative-ready date), which is modest added value, but says nothing about assumptions, precision, or edge cases for a pure computation.

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 first sentence is well front-loaded and efficient, but the trailing promotional URL ('See the full version at ...') is pure waste for an agent selecting a tool and dilutes the definition.

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 100% schema coverage on all four parameters, the description needn't explain returns or inputs, and annotations cover the safety profile. The one real omission is sibling differentiation, which overlaps with usage guidelines rather than leaving the call itself under-specified.

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% and every parameter (audience, dailyImpressions, freqCap, currency) is already documented in the schema, including the ISO 4217 pattern and the omit-to-show-plain-numbers behavior. The description adds no parameter meaning beyond that, so the baseline 3 applies.

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: forecast days until an audience hits its fatigue frequency ceiling, plus the fresh-creative-ready date. Clear on its own, but it never distinguishes itself from close siblings like ad_frequency_risk_checker or creative_testing_duration_forecaster, so an agent cannot route between them from the text 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?

No when-to-use guidance, no prerequisites, and no mention of the alternative calculators that overlap heavily (ad_frequency_risk_checker, channel_saturation_estimator). The agent must infer the trigger scenario entirely from the 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 readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered by structured data. The description adds the useful fact that the result is bucketed into three qualitative risk tiers, but omits anything about threshold boundaries or cost (e.g. currency handling) 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?

The first sentence is front-loaded and efficient, but the second sentence is a promotional link to an external site rather than task-relevant information. It is short overall, yet one of two sentences does not earn its place for an agent trying to invoke the tool.

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, return values need not be explained, and the description covers what is computed and the categories produced. Two required params and one optional are all schema-documented, so the definition is nearly complete for a stateless calculator; only the absence of threshold context is a minor gap.

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 impressions, reach, and currency are each documented in the schema; the description only names two of the three inputs. With the schema doing the heavy lifting, the baseline of 3 is appropriate and the description adds no extra syntax or unit 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 states a specific verb and resource ('Calculate average ad frequency from impressions and reach') plus the output judgement ('healthy, caution, or fatigue territory'), so the tool's function is unambiguous. It does not, however, differentiate itself from close siblings such as ad_creative_fatigue_forecaster or channel_saturation_estimator, leaving the agent to infer 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 when-to-use or when-not-to-use guidance and no named alternative among the many ad-metrics siblings. The context of the calculation is implied by the name, but nothing tells an agent when this checker is the right choice over a fatigue forecaster or saturation estimator.

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 destructiveHint=false, so the safety profile is fully covered structurally. The description adds nothing beyond that – no note on assumptions behind the estimate, input validity ranges, or how the two leakage categories are combined – so it does not earn credit for extra behavioral context.

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 purpose sentence is short and front-loaded, which is good. The second sentence is a promotional link to the hosted calculator rather than something that helps an agent invoke the tool, so it only partially 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 read-only calculator with an output schema and 100% parameter coverage, the description is sufficient: the agent knows what is computed and what inputs are required. Nothing critical is missing, though the absence of any usage context keeps it from being fully rounded.

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 all four parameters (including the optional ISO 4217 currency code and the two percentage inputs) are already documented. The description adds no syntax, format, or range detail beyond the schema, so baseline 3 applies.

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 ('Estimate') and a specific resource (monthly ad budget that leaks to fraud and tracking/attribution waste), which is enough to distinguish it from siblings like roas_calculator or performance_marketing_margin_protector. It doesn't explicitly name those siblings, but the scope is clear.

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 when-to-use guidance, no prerequisites, and no named alternative among the many adjacent ad-spend tools in the sibling list. The second sentence is purely a link to a web version, not usage instruction.

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 behavior, so the safety profile is covered. The description adds that supplying a prior period yields a trend and an incremental ratio, which is useful behavioral detail, but nothing about error handling or result shape.

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 sentences, purpose front-loaded, no filler. The trailing promotional URL does not help tool selection but is brief enough not to materially hurt the structure.

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 values need not be explained, and the full parameter set is covered by the schema. For a stateless calculator the definition is essentially complete, missing only routing context against sibling calculators.

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 all five parameters are already documented, including the currency format and the net-sales definition. The description restates adSpend/netSales/prior period but adds no syntax or edge-case meaning beyond the schema, so the baseline of 3 applies.

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 resource (advertising-to-sales ratio), plus the two required inputs and the optional prior-period extension. An agent knows exactly what this computes, though it never names a sibling (e.g. roas_calculator) to distinguish the many adjacent calculators.

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 when-to-use or when-not-to-use guidance and no named alternative. With dozens of sibling ratio/ROI calculators, the description leaves the agent to infer that this is the right one for A/S ratio from the name alone.

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 destructiveHint=false, so the safe read-only calculation profile is covered. The description adds the enumeration of measured dimensions but no extra behavioral context such as assumptions behind the estimate, and an output schema already handles return values.

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 sentences that front-load the core outcome, followed by a link to the full version. Efficient, though the promotional URL is a minor non-essential element rather than tool-selection 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 parameterized calculator with a full output schema and 100% param coverage, the description is sufficient: it conveys what is being computed and from which dimensions. The missing piece is when to select it among a large family of sibling calculators.

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 every parameter (including the four enums and the currency pattern) is documented in the schema itself. The description names the friction categories but adds no syntax, format, or enum-level meaning beyond what the schema provides, so the baseline of 3 applies.

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 (quantify) and resource (meetings and revenue lost from the SDR-to-AE hand-off) and enumerates the four friction dimensions it measures. This clearly distinguishes it from nearby siblings like lead_routing_delay_cost_calculator or mql_to_sales_disconnect_analyzer.

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 its use case (measuring SDR-to-AE hand-off friction) but never states when to pick this tool over the many alternative funnel/leak calculators, nor any prerequisites or exclusions. Usage is inferable from context but not explicitly guided.

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=true, idempotentHint=true, and destructiveHint=false, so safety and repeatability are covered. The description adds that the result is a monthly traffic/lead requirement, but says nothing about units, sign handling, or edge cases like zero conversion rates that would materially affect how an agent interprets inputs.

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 first sentence is front-loaded, dense, and carries the entire semantic payload with no waste. The second sentence is a low-value promotional link rather than necessary invocation guidance, which keeps this short of a 5.

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, return values need not be described, and parameters are fully covered by the schema, leaving little for the description to carry. Behaviorally it is a deterministic, non-destructive calculation, so the only real gap is the absent usage framing relative to the many sibling calculators.

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 all five parameters are already documented in the schema, including the currency pattern and the percentage semantics. The description only restates ACV and close rates at a high level, adding no format or unit detail beyond the schema; 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 gives a specific verb and a precise computation chain: back-calculate from an annual revenue goal, through ACV and close rates, to monthly traffic and leads. It is clearly distinguishable from most siblings by its reverse-solving framing, though it never names or contrasts a close alternative such as mql_calculator or acv_weight_planner.

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: an agent can infer it applies when a revenue target and funnel conversion rates are known, since the required inputs are enumerated in schema. There is no explicit when-to-use statement, no prerequisites, and no routing to or away from alternatives.

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, so the safety profile is fully covered. The description adds that it computes a valuation range across four multiple types, but says nothing about the calculation method or edge cases; with annotations carrying the safety burden, a 3 is appropriate.

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 first sentence is well front-loaded and efficient. The second sentence is a promotional link to an external site that contributes nothing to correct invocation, so it does not fully earn 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?

With an output schema present and 100% parameter description coverage, the description need not explain return values or parameter formats. It adequately covers the tool's scope as a pure computation, though it could mention how the multiples combine into a range.

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 all six parameters (including the optional currency and customMultiple) are already documented in the schema. The description names the multiple types but adds no syntax, units, or format detail beyond the schema; baseline 3 applies.

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 ("apply") and resource (ARR multiples) and names the output (valuation range), so the core purpose is unambiguous. However, it never distinguishes itself from near-neighbors like saas_valuation_multiple_predictor or mrr_to_arr_calculator, so sibling routing relies on name inference.

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 when-to-use guidance, prerequisites, or alternative tools are named. The only contextual cue is that customMultiple is optional, which the schema already conveys.

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=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds the useful detail that it models a 'halving' recovery scenario and links to an external full version, but reveals nothing about determinism, rate limits, or input constraints beyond that.

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 sentences, front-loaded with the core computation before the recovery scenario and the external link. Nothing is wasted, though the trailing URL sentence is purely promotional.

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, and annotations cover the safety profile. It tells the agent what is estimated and what secondary figure is produced, which is sufficient for calling a four-parameter read-only calculator.

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 acv, currency, delayWeeks, and dealsPerYear are already fully documented by the schema. The description maps conceptually onto those inputs (signature-to-go-live gap, annual deal volume) but adds no format, range, or example detail 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?

States a specific verb ('Estimate') and a precisely scoped resource ('revenue delayed each year by a slow onboarding gap between signature and go-live, and what halving it recovers'). It does not explicitly differentiate from adjacent siblings such as lead_routing_delay_cost_calculator, so it lands just below the top mark.

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?

Provides no when-to-use guidance, no prerequisites, and no named alternatives. The domain is implied by the wording, but the agent gets no explicit routing signal versus the many other delay/cost calculators in the sibling list.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful context beyond them: it discloses the return shape (band, target range, meaning) and warns that outputs are heuristics rather than guarantees, which is exactly the kind of reliability caveat an agent needs.

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 tightly packed sentence, front-loaded with the verdict action and structured as claim-then-scope-then-caveat. The long metric enumeration is necessary for scope but is the only thing making it bulky.

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 lookup tool with no output schema, the description adequately covers what is returned and the caveat on precision, and the schema covers parameters fully. The single real gap is the absence of any routing guidance relative to the many sibling benchmarking/calculation 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 100% and the schema itself carries the enum values plus unit conventions (percent metrics take percentages, ratios take the multiple) and the segment/grossMarginPct usage notes. The description adds no parameter detail beyond that list of metric names, so the baseline 3 applies.

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 action (judge whether a number is good) and the resource (a named set of 14 marketing/SaaS metrics), and it spells out what comes back: band, target range, and interpretation. The metric enumeration makes it distinguishable from the single-metric sibling calculators, though it never explicitly contrasts itself with 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?

There is no when-to-use guidance and no routing against the many overlapping siblings (ltv_cac_calculator, ltv_to_cac_ratio_health_grader, saas_magic_number_calculator, roas_calculator, etc.). The only framing is the caveat 'Rules of thumb, not guarantees,' which sets expectations but does not tell an agent when to pick this tool over those.

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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds that the tool computes a derived break-even value beyond a plain comparison, which is minor extra context; it says nothing about output shape or units handling beyond what annotations imply.

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?

Front-loaded with the core comparison and break-even outcome in one dense sentence, which is efficient. The trailing promotional link sentence is not strictly functional but is brief.

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 values need not be described, and annotations cover the safety profile while the schema covers all parameters. The description states the key derived output (break-even exit value), making it essentially complete for a stateless calculator.

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 both the four required exit/ownership inputs and the optional currency code are already documented in the schema. The description adds no syntax, unit, or range meaning beyond that, so the baseline 3 applies.

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 specific verbs (compare, find break-even) and concrete resources (bootstrapped exit take-home vs venture-backed diluted exit take-home). An agent can tell it apart from generic valuation siblings like arr_multiple_calculator or saas_valuation_multiple_predictor without opening any schema.

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 scenario (deciding whether raising pays off) is implied but never stated as an explicit when-to-use, and no alternative or exclusion is named. Adequate but leaves the agent to infer context.

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 a safe, read-only, idempotent, closed-world operation, so the description owes little on safety. It does add that results are a heuristic framed by Binet & Field long/short research and only a 'directional guide', which usefully tempers how the output should be trusted, but it says nothing about output shape or limitations beyond that.

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 first sentence is well front-loaded and earns its place. The second is a promotional link to an external calculator page, which carries no operational value for an agent deciding how to invoke the tool.

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, return values need not be documented, and annotations cover the safety profile. What remains missing is routing context — when this beats the many similar allocation tools — and any note on how to interpret the brand/performance split, leaving it adequate but thin.

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% — stage, budget, and currency all have schema descriptions, and stage's enum values are already explained there. The description adds no syntax or semantic detail beyond noting stage drives the split, so baseline 3 applies.

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 (split) and resource (marketing budget) with the two output categories (brand vs performance) and the driving input (company stage). It is clear what the tool computes, though it never distinguishes itself from near-neighbors like cross_channel_ad_spend_allocator or marketing_budget.

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 no when-to-use guidance, no preconditions, and no named alternatives despite a crowded sibling set of budget/allocation calculators. 'Based on company stage' hints at the input but not at when an agent should pick this tool over the others.

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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered structurally. The description adds the algorithmic character of the tool (a month-by-month simulation producing a break-even month count and a bridge-cash figure), which is real context beyond the annotations, but says nothing about assumptions, rounding, or edge cases (e.g. zero growth, negative margin).

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 core computation is front-loaded in a single dense sentence with no filler. The trailing promotional URL ('See the full version at...') is arguably outside the tool's scope and is the one element that does not earn 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?

With an output schema present the description need not explain return values, and annotations cover safety, so the only real burden is purpose and inputs — both adequately handled. The missing piece is disambiguation from the many financial-modeling siblings, which leaves a small completeness gap.

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 all five parameters are already documented in the schema, and the description only echoes growth rate and gross margin. No additional meaning (units beyond the schema, defaulting behavior, currency handling) is added. Baseline 3 is correct when the schema carries the load.

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 computation: month-by-month simulation of when gross profit covers fixed burn plus the cash needed to bridge the gap. That is a concrete verb+resource and distinguishes it from generic calculators. However, with 100+ siblings including close cousins like growth_runway_extension_simulator and run_calculator, it never explicitly differentiates itself from those alternatives.

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 when-to-use, when-not-to-use, or alternative-tool guidance. The scenario is implied by the inputs (a burn/growth scenario) but an agent choosing between this and run_calculator, growth_runway_extension_simulator, or rule_of_40_sandbox gets no routing help.

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=true, idempotentHint=true, and destructiveHint=false, so safety behavior is covered. The description adds that results are computed on both a gross-margin and a raw-revenue basis, which is useful output context, but it discloses nothing further about limits, assumptions, or edge cases.

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 tight sentences with the computational purpose front-loaded and the calculation basis highlighted. The trailing link is promotional but adds a documented 'full version' reference, so it is not purely wasted.

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 values need not be explained, and an idempotent read-only calculator is a simple tool. However, the complete absence of usage guidance for a CAC-metric tool surrounded by similar siblings leaves a real gap, so it is only minimally 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?

Schema description coverage is 100%, so the schema already documents cac, monthlyArpa, grossMarginPct, segment, and currency fully. The description adds no syntax or format detail beyond what the schema provides, so the baseline of 3 applies.

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 resource ('months to recover fully-loaded CAC'), and adds a distinguishing scope detail: gross-margin basis versus raw-revenue basis. It is clearly a CAC payback calculator, though it never names siblings like ltv_cac_calculator or cpa_to_cac_scalability_matrix to disambiguate.

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 no when-to-use context, prerequisites, or alternatives. With many neighboring CAC/LTV calculators in the sibling list, the agent gets no guidance on when this one is preferred over ltv_cac_calculator or cpa_to_cac_scalability_matrix.

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=true, idempotentHint=true and destructiveHint=false, so the safety profile is fully covered. The description adds no behavioral context beyond that – nothing about currency handling, defaulting behavior when currency is omitted, or how the two figures relate. The second sentence is a promotional link, not 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 first sentence is tight and front-loaded, but the second sentence is a marketing URL that does not help an agent invoke the tool and does not earn its place. Net size is fine; content allocation is not.

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, return values need not be described, and annotations cover safety, so the remaining gaps are usage context and a clear statement of the calculation model. The definition is adequate but leaves the agent to guess when this calculator beats its many siblings.

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%, including a useful hint (industry average abandonment near 70%) and pattern guidance for the currency code, so the schema carries the parameter burden. The description adds no extra meaning, which is the baseline-3 case.

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 revenue lost to cart abandonment plus recoverable revenue from a win-back flow. That is more concrete than a bare name restatement, but it offers no differentiation from the many adjacent calculators in the sibling list (e.g. roas_calculator, mobile_checkout_friction_tester, cpl_cpa_calculator).

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 contains no when-to-use guidance, no prerequisites, and no mention of alternatives such as run_calculator or find_calculator. The agent must infer the trigger scenario entirely 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 readOnly=true, idempotent=true, destructive=false and openWorld=false, so the safety profile is covered. The description adds no behavioral context beyond that — no note on determinism, currency handling, or interpretation of the result. For a pure calculation tool with full annotation coverage, a 3 is appropriate.

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 core purpose is front-loaded in a single efficient sentence. The second sentence is a promotional link to an external site that does not help an agent invoke the tool, which slightly detracts from strict conciseness but the overall length is small.

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 and annotations cover the safety profile, so the description needn't explain return values. For a self-contained calculation the essential input semantics are covered by the schema, leaving the definition complete enough to call 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 description coverage is 100%, so all four parameters (currentCpa, monthlyInflationPct, maxCpa, currency) are already documented in the schema. The description adds no syntax, unit, or default information beyond what the schema provides, so the baseline 3 applies.

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 outcome: 'Project how many months until a channel's compounding CPA inflation pushes it past your max viable CPA.' That is a precise, distinguishable purpose. It doesn't name or differentiate against any sibling tool, keeping it 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?

There is no guidance on when to use this versus alternatives (e.g. cpa_to_cac_scalability_matrix, ltv_to_cac_ratio_health_grader), no prerequisites, and no exclusions. Usage is only weakly implied by the computation described.

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/openWorld/non-destructive, so the safety profile is covered. The description adds genuine context beyond that: each returned time carries a link that opens the booking form with the time pre-selected, and the actual confirmation/booking happens on the site, not through this tool. That clarifies the read-only boundary of the call.

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, front-loaded with the core action before the mechanics and the usage condition. Each sentence earns its place, though the consultant credential aside ('fractional CMO and RevOps consultant') is mildly promotional rather than operational.

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 no output schema, the description carries the burden of explaining returns, and it does so adequately by describing the shape of each entry (a time plus a booking link). Combined with fully documented optional params and read-only annotations, an agent has what it needs to invoke and interpret the tool.

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 days (1-21), timezone (IANA), and meetingType fully documented in the schema. The description adds no parameter-level meaning of its own, so the baseline 3 is correct given the schema does the heavy lifting.

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+resource ('List open times for a free call with Rahul D Sarker') with the source of truth ('live from his calendar'). This is instantly distinguishable from the entire sibling set, which is calculators and graders rather than availability lookups.

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?

Gives explicit usage contexts: 'Use when someone wants to talk to Rahul, get help with their marketing or RevOps, or book a consultation.' Clear triggering conditions, though it names no alternatives or when-not-to-use condition (none of the siblings overlap, so this is a minor gap).

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the remaining burden is methodological. The description usefully discloses the estimation assumption and its rough/proxy nature, which tells the agent the output is an approximation rather than measured data. It does not discuss precision limits or currency handling, keeping it below 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?

Two sentences with the purpose front-loaded, followed by the key assumption. The trailing promotional URL adds no functional value for tool selection, a minor inefficiency rather than a structural flaw.

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 deterministic calculator with a full output schema and 100% parameter coverage, the description supplies exactly the missing piece an agent needs to interpret results: the share-of-voice-to-spend assumption. Nothing required for correct invocation is absent.

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% – spend, both SOV percentages and the ISO 4217 currency pattern are all documented in the schema. The description adds no parameter-level detail (e.g. whether percentages are 0-100 or 0-1), so the baseline 3 applies.

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 verb (Estimate) and resource (competitor's ad spend) plus the input method (share-of-voice data), which separates it from siblings like ad_spend_waste_calculator and cross_channel_ad_spend_allocator that also deal with ad spend. It does not name an alternative sibling explicitly, so it stops 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 states the modeling assumption (spend maps roughly to share of voice within the same auction), which functions as a validity condition for when the result is meaningful. However, it never says when to prefer this over related tools such as google_search_impression_share_value_estimator or impression_share_opportunity_matrix, leaving usage implied.

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 destructiveHint=false, so the safety profile is fully covered by structured data. The description echoes the computational scope but adds nothing about determinism, rounding, or limits. The 'see the full version' link hints this may be a reduced build without explaining what is reduced.

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?

One substantive sentence front-loads the purpose and outputs with no padding. The second sentence is a promotional URL rather than task-relevant guidance, which slightly dilutes the signal but does not obscure the core description.

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, return values need not be explained, and the 100%-covered input schema handles parameters. The description covers the tool's scope adequately for a read-only calculator, though it omits any hint of constraints or its relationship to sibling forecasting 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 100%, so all seven parameters are documented in the schema itself, including the 'paper' enum and its ~1.8x multiplier. The description adds no parameter-level meaning, which matches the baseline 3 when the schema does the heavy lifting.

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 ('Predict') and resource (legal redlines) and enumerates the three outputs: duration, quarter-end slippage, and revenue at risk. This differentiates it from neighbors like sales_cycle_length_forecaster and b2b_implementation_delay_cost_calculator. It stops short of naming a sibling it is not, so a 4 rather than 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 what it computes but never says when to reach for it versus alternatives such as sales_cycle_length_forecaster or b2b_implementation_delay_cost_calculator. No prerequisites, exclusions, or contextual triggers are given. Usage must be entirely inferred from the purpose sentence.

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, destructiveHint false, and openWorldHint false, so the safety profile is well covered. The description adds no behavioral context beyond this (e.g., no mention of rate limits, auth, or side effects), but it also does not contradict the annotations. With annotations carrying the behavioral burden, a 3 is the minimum viable.

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 first sentence is concise and front-loaded with the tool's purpose. However, the second sentence is a promotional link to an external calculator, which does not help an agent invoke the tool and therefore does not earn 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?

Given the presence of an output schema, full schema description coverage, and comprehensive annotations, the description is nearly complete for a simple calculator. It could be improved by noting the currency formatting and its lack of side effects, but the structured data already covers those 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?

Schema description coverage is 100%, meaning the schema itself documents all four parameters (visitors, conversions, target, currency). The description adds no parameter-level meaning beyond what the schema provides, so the baseline of 3 applies.

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 (calculate) and resources (conversion rate and traffic needed for a target), making the tool's function clear. However, it does not explicitly differentiate this calculator from the many sibling calculators, so it stops 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?

No when-to-use guidance or alternatives are provided. The description only states what the tool does; it never says when an agent should choose this over sibling calculators like cpl_cpa_calculator or roas_calculator, nor does it mention any prerequisites 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?

Annotations already declare this a read-only, idempotent, non-destructive computation, so the safety profile is covered. The description usefully adds the model's core assumption (a per-doubling decay rate governing CPA inflation), but says nothing about output shape, precision, or edge cases like zero decay.

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 operative sentence is front-loaded, dense, and free of filler. The trailing sentence is only a promotional link to an external page, which contributes little to correct invocation but costs just one short line.

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 values need no explanation, and all parameters are documented at 100% coverage. The description supplies the essential conceptual model for interpreting and setting decayPct, leaving only minor gaps such as assumptions about compounding behavior.

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 all four parameters including the optional currency pattern are already documented in the schema. The phrase 'per-doubling decay rate' mirrors the schema's decayPct description without adding new syntax or constraints, which is the expected baseline when the schema carries the 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 names a concrete verb ('Project') and a specific resource outcome (CPA/CAC inflation under doubling/tripling spend), which clearly separates it from generic CPA calculators like cpl_cpa_calculator. It stops short of naming a sibling alternative, so an agent must infer the distinction, but the modeled scenario is precise enough to route correctly.

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 when-to-use versus when-not-to-use guidance and no referenced alternative among dozens of adjacent CAC/LTV tools. The scenario described implies a use case but gives the agent no explicit selection 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, idempotentHint, and destructiveHint=false, so the safety profile is fully covered structurally. The description adds only the set of derived metrics, which is modest value for a pure deterministic calculator; there is little behavioral surface left to disclose.

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 purpose is front-loaded in the first sentence with no wasted preamble. The trailing link to an external 'full version' is promotional rather than operational and adds no invocation value, but it is brief enough not to undermine the structure.

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 values need not be explained, and the input surface is simple and fully documented. Combined with annotations that cover the safety profile, the definition is essentially complete for a single-step calculator, with the only gap being routing guidance against sibling metrics 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 100%, so all four parameters (spend, leads, convPct, currency) are already documented, including the ISO 4217 pattern and units. The description restates the inputs at a high level without adding format, unit, or edge-case meaning beyond the schema, so the baseline 3 applies.

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 (Calculate) and enumerates the exact outputs (cost per lead, expected customers, cost per acquisition) plus the inputs. However, it does not differentiate this tool from adjacent siblings such as cpa_to_cac_scalability_matrix, cac_payback_period_matrix, or ltv_cac_calculator, leaving the agent to infer boundaries from 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 when-to-use guidance, no stated preconditions, and no mention of alternatives among the many marketing-metric calculators in the sibling list. The description says what it computes but never says when to reach for it over a neighboring tool.

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, and closed-world, so the safety profile is fully covered. The description adds only the deterministic input-to-output relationship of the formula; it says nothing about edge cases (zero spend, zero CPA), whether the result is a single day count or a range, or how currency affects the output. Adequate but not additive 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?

The first sentence is well front-loaded and information-dense, but the trailing sentence is purely promotional, pointing to an external site (https://rahuldsarker.co/...) that an agent cannot use and that does not help invocation. One sentence earns its place; the second is waste.

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, return values need no explanation, annotations cover safety, and all four required inputs are enumerated along with the optional currency. The gap is that it does not flag any boundary condition for a math tool where division by spend or CPA is plausible.

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 prose restates the same four inputs in natural language and adds no syntax, units, or range constraints beyond what the schema already documents.

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 verb and output ('Forecast how many days an ad creative test needs to reach a sound sample size') and enumerates the exact inputs that drive it. That is enough to separate it from near-neighbors like ad_creative_fatigue_forecaster and ab_test_significance_calculator, though it never names an alternative explicitly.

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 when-to-use statement, no prerequisites, and no mention of when this should be chosen over the many sibling calculators (e.g. ab_test_significance_calculator, ad_creative_fatigue_forecaster). The ad-creative-test framing implies a context but never states it as 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description does not contradict it. The description confirms the output is an annualized loss/capacity figure, but adds nothing about determinism, units of the result, or how the currency omission behaves.

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, front-loaded with the outcome the agent cares about. The trailer pointing at an external full version is a slight dilution but does not obscure the core 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?

An output schema exists and annotations cover safety, so returns and side effects need no elaboration. What is missing is the one thing the structured fields cannot supply: how this differs from the sibling crm_roi_calculator, leaving selection ambiguous.

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 reps, hoursWastedPerWeek, hourlyCost and currency are all documented in the schema itself. The phrase 'each year' mildly clarifies that the weekly input is annualized, but that is marginal added meaning, so the baseline 3 applies.

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?

Specific verb (quantify) plus specific outputs (rep hours and revenue lost to dirty CRM data, selling capacity freed by cleanup), which is far more than a restatement of the name. It does not distinguish itself from the nearby sibling crm_roi_calculator, so an agent must infer which CRM-ROI tool applies.

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 never states when to reach for this tool instead of crm_roi_calculator, data_enrichment_value_predictor, or the other ROI calculators in the catalog. The only secondary content is an external link to a 'full version', which is not usage 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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered by structured data. The description adds nothing beyond that – no note on units, rounding, or interpretation of the result – but for a pure calculator the residual behavioral burden is small, so this is adequate rather than deficient.

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 first sentence is tight and front-loaded. The second sentence is purely a promotional link to the author's site and carries no operational value for an agent, so half the description does not earn 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?

With an output schema present and complete parameter documentation, the description need not explain return values, and the annotations cover safety. What remains missing is the disambiguation from sibling ROI tools, which is the one thing structured fields cannot supply.

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 all seven parameters (including the optional currency code) are already documented in the schema. The description contributes no additional parameter meaning, which is the expected baseline when the schema does the heavy lifting.

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 action (weigh cost against lift) and the exact resource (CRM subscription plus implementation cost vs. win-rate lift), so the agent knows what the tool computes. It does not, however, distinguish itself from the closely named sibling crm_cleanup_roi_calculator, which an agent could easily confuse it with.

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 reach for this tool versus the many nearby ROI calculators (crm_cleanup_roi_calculator, ltv_cac_calculator, acv_weight_planner). No prerequisites, no exclusions, no alternatives are named.

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, and non-destructive, so the safety profile is fully covered by structured data. The description adds only that the output is a suggested 'starting' split (heuristic, not authoritative), which is mildly useful but not rich behavioral context. A 3 is appropriate when annotations carry the safety burden.

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?

Front-loaded purpose in the first sentence with no wasted words. The second sentence is a promotional link to the 'full version' that does not help an agent invoke the tool, which slightly dilutes the structure but is brief.

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 values need no explanation, and annotations cover the safety profile. Purpose and the two required inputs are stated, leaving only minor gaps around usage context and the optional currency parameter.

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 budget, acv, and currency are all documented in the schema with the ISO 4217 pattern and examples. The description mentions budget and ACV but adds no syntax or format detail beyond the schema, and omits currency entirely. Baseline 3 applies when the schema does the heavy lifting.

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: 'Suggest a starting Google/Meta/LinkedIn budget split'. The channel specification distinguishes it from generic budget siblings like brand_vs_performance_budget_allocator and marketing_budget. It does not explicitly name an alternative, so it falls 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 names the two inputs ('based on total budget and average contract value') and implies a planning-stage use via 'starting', but gives no when-to-use guidance, no conditions, and no alternatives among the many budget-related siblings. An agent gets no routing help.

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, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds no behavioral context beyond that – nothing about determinism, units, or what the estimate represents operationally. It is a pure stateless calculator, so the annotation bar is low, but the description contributes nothing new.

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 first sentence is efficient and front-loaded. The second sentence is a promotional pointer to an external 'full version' URL, which does not help an agent invoke the tool and dilutes the definition. Appropriate length overall, but one sentence does not earn 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?

With a 100% covered schema, full annotations, and an output schema that carries the return shape, the description only needs to frame the calculation, which it does. It is largely complete for a self-contained estimator, with the minor gap being no explicit positioning against sibling expansion 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 100%, so the schema already documents all five parameters. The description's phrasing ('single-product customer base', 'expansion ARR') loosely maps to singleProductSharePct and crossSellAcv but adds no format or unit detail beyond the schema. Baseline 3 applies.

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 verb (Estimate) and resource (expansion ARR from cross-selling a second product into the existing single-product base). This is fairly precise, but it does not explicitly distinguish itself from close siblings like customer_expansion_revenue_matrix or expansion_revenue_impact_simulator, so it stops 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 states what the tool computes but gives no when-to-use guidance, no prerequisites, and no mention of alternatives among the many expansion/revenue siblings. An agent is left to infer the appropriate context entirely.

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 this as a safe, read-only, idempotent, closed-world computation. The description adds that the score is derived from an actual WCAG contrast ratio plus size and placement, which clarifies the deterministic scoring basis. It says nothing about score ranges, thresholds, or output shape, so it adds only modest value beyond the 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?

The scoring sentence is well front-loaded and efficient, but the trailing promotional URL consumes roughly a third of the text without helping an agent invoke the tool. Trimming it would make this a tight, single-purpose definition.

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 is not obligated to explain return values, and it covers all three scoring inputs plus the contrast basis. The unmentioned currency parameter is documented in the schema, and annotations cover the safety profile, so nothing essential 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%, including enum semantics for size and placement and the hex format and ISO currency pattern, so the schema carries the parameter burden. The description confirms the three scoring inputs but adds no format or constraint detail beyond what the schema already provides — the correct baseline of 3.

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 (score) and resource (CTA button visibility) and names the exact factors used: WCAG contrast ratio, size, and placement. An agent can distinguish it from near-neighbors like typography_legibility_grader or landing_page_vs_ad_match_quality_auditor without opening the schema.

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 when-to-use or when-not-to-use guidance, no mention of prerequisites, and no routing to or away from any sibling tool. The only extra sentence is a promotional URL, not usage context.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. The description usefully defines what 'net expansion' means (upsell + cross-sell minus contraction) and the horizon (1/2/3 years), but adds nothing about precision, rounding, or edge cases such as negative expansion.

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 core sentence is front-loaded and dense with useful specifics. The trailing external URL is promotional rather than invocation-relevant, a minor waste, but the definition stays short and readable.

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 values need not be described. For a three-parameter, read-only deterministic calculator, the description supplies the formula semantics and horizon needed to call it correctly; only the lack of usage routing is a gap.

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%, so all three parameters are documented in the schema itself (arr, currency ISO 4217, monthlyExpansionPct). The description clarifies that monthlyExpansionPct is net of contraction and excludes new logos, which slightly enriches the schema wording, but the baseline of 3 is appropriate when the schema carries the load.

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 computation (compound net monthly expansion revenue forward 1, 2, and 3 years from current ARR) and adds a distinctive constraint ('no new logos') that separates it from siblings like expansion_revenue_impact_simulator or net_revenue_retention_forecaster. It is clear what the tool does, though it never explicitly names a sibling alternative.

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 when-to-use framing, no prerequisites, and no steering toward or away from the many adjacent calculators (cross_sell_opportunity_estimator, ltv_growth_multiplier_simulator, expansion_revenue_impact_simulator). The agent must infer fit from the purpose sentence alone.

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, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered structurally. The description adds only that the output includes a hiring gap, and its second sentence points to an external 'full version', implying this may be a trimmed variant — mildly relevant but no detail on determinism, rounding, or units.

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 purpose sentence is front-loaded and efficient, but the second sentence is a promotional URL that conveys almost no invocation value and dilutes the definition.

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 annotations covering the behavioral profile, the description need not explain return format. For a deterministic single-purpose calculator the purpose statement is sufficient, missing only usage context that a slightly richer description could supply.

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% and all four parameters (including optional currency) are documented in the schema itself. The description contributes no additional parameter meaning, so the baseline 3 applies.

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 first sentence names a specific verb (compare) and resource (CSM account load vs. healthy book size) and states the two outputs: capacity utilization and hiring gap. It's clear what the tool computes, though it never explicitly differentiates itself from adjacent planning calculators like sdr_capacity_and_inbound_quota_planner.

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 when-to-use guidance, no stated prerequisites or inputs context, and no routing to or away from alternatives. The agent is left to infer applicability purely from the purpose sentence.

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=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds that it performs a cost comparison and calculates net savings and ROI, but this is largely restated by the title and output schema and does not disclose additional behavioral traits like constraints or data sources.

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-loading the core action in the first sentence. The external link is short and does not disrupt readability, though it may be unnecessary for an AI agent.

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 calculator with a rich output schema and full parameter descriptions, the description adequately conveys the purpose. It does not need to explain return values or parameter formats because those are covered elsewhere, and no critical behavioral or usage details are missing for correct invocation.

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 itself documents all six parameters in detail. The description does not mention any parameter, which is acceptable given the comprehensive schema, but it adds no parameter-level meaning beyond what is already structured.

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 (compare) and resources (manual rep research cost vs enrichment tool subscription cost), plus the computed outcomes (net monthly savings and ROI). It does not name an alternative sibling tool, but the domain is specific enough to distinguish it from most other calculators.

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 guidance, no prerequisites, and no mention of alternative tools or when not to use this one. The description implies a scenario but leaves selection among the many calculator siblings 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds the output framing (recognized to date vs. remaining liability) but omits assumptions such as rounding, mid-month proration, or what happens when monthsElapsed exceeds termMonths.

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 first sentence is efficient and front-loaded. The second sentence is a promotional URL pointing off-platform, which does not help an agent invoke the tool correctly and dilutes the definition.

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 annotations and an output schema present, the description needn't explain safety or return values, and it covers the core computation. It remains silent on assumptions and boundary behavior for a 4-parameter financial calculator, leaving a modest but real gap.

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 parameter documented in the schema including the ISO 4217 currency pattern. The description adds no format, unit, or edge-case detail beyond what the schema already provides, so the baseline 3 applies.

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: straight-lining an upfront payment across a contract term to derive revenue recognized to date versus remaining deferred liability. An agent can identify the computation immediately. It does not, however, distinguish itself from conceptually adjacent siblings such as mrr_bridge_planner or net_revenue_retention_forecaster.

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 statement of when to choose this tool over alternatives, no prerequisites, and no exclusions. Usage must be inferred entirely from the description's formula summary.

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 dual-mode framing, but says nothing about accuracy caveats, rounding, or how omitted optional inputs behave. Some added value over annotations, not much.

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 core sentence is dense, front-loaded and earns its place. The trailing promotional URL link is not operationally useful to an agent and slightly dilutes an otherwise efficient definition.

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 full schema descriptions, the agent has everything needed to invoke this correctly; the description only needs to frame scope, which it does. Minor gap: it never states that the mode is selected by supplying winRatePct.

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 every parameter is already documented in the schema, including the currency pattern and the winRatePct 'B2B only, omit for ecommerce' rule. The description adds no parameter-level meaning beyond that; baseline 3 applies.

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 ('Estimate') plus the exact outputs (monthly revenue, ROI, revenue per email, revenue per subscriber) and the resource (an email programme). The named inputs and modes make it trivially distinguishable from near-neighbours like crm_roi_calculator or roas_calculator.

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 names the two operating modes (ecommerce vs B2B pipeline), which implies how to configure the call, but gives no explicit when-to-use or when-not-to-use guidance relative to the many sibling ROI calculators. Usage is inferable, not 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 readOnlyHint, idempotentHint, destructiveHint false, and openWorldHint false, covering the safety profile. The description adds the behavioral insight that cost-to-serve does not drop with price, which explains the model's logic. It does not add operational details like rate limits or auth, so it is a modest addition.

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 sentences: the first front-loads the purpose, and the second points to an external full version. The link may be promotional rather than essential for invoking the tool, slightly reducing efficiency.

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 a complete input schema and an output schema, the description need not detail parameters or return values. It provides enough context for a calculation tool, though it lacks guidance on interpreting or applying results.

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 all five parameters are documented in the schema. The description does not add any parameter semantics beyond what the schema provides, so the baseline of 3 applies.

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 ('Show') and resource ('lifetime profit an enterprise discount gives away'), and adds the rationale that cost-to-serve does not drop with price. It does not explicitly differentiate from sibling calculators like gross_margin_impact_calculator, so it is clear but not fully distinguishing.

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 when-to-use guidance or alternatives are mentioned. The implied context is evaluating an enterprise discount, but the description does not say when to choose this tool over other pricing or margin calculators.

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 that this is a safe, read-only, idempotent, closed-world operation. The description adds useful context by naming the inputs that drive the estimate, but it does not disclose output format, rate limits, or other behavioral traits beyond the 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?

The description is front-loaded with the core purpose and is only two sentences long. The second sentence is an external link to a fuller version, which adds little for an agent but does not bloat the definition.

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 a full output schema and complete input schema coverage, so the description does not need to explain return values. It adequately states the purpose and inputs for a simple read-only estimator, though it could say more about when to use it.

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