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

No annotations are provided, so the description bears the full behavioral-disclosure burden. It adds some useful context by saying the audit is deterministic, covers a 90-day window, and expects Stripe 2025-03-31.basil item-level subscription periods, but it does not state whether the tool is read-only, what permissions or auth are required, whether it mutates data, or what its output/error behavior is.

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 definition is a single front-loaded sentence that states the core action and scope without repetition or filler. It is appropriately sized for a tool with no annotations and no output schema, though the sentence is dense and packs technical details into one long clause.

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 complex audit tool with no annotations, no output schema, and only 67% parameter-description coverage, the description is incomplete. It identifies the audit scope and primary input categories but omits the return/report shape, safety profile, prerequisites, and semantics for costPerEventCents and dunningGracePeriodDays.

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 67%: 'demo', 'disputes', 'customers', and 'usageEvents' have schema descriptions, while 'costPerEventCents' and 'dunningGracePeriodDays' do not. The description mentions subscriptions, usage events, and disputes, aligning with three parameters, but it does not add meaning for the two undocumented economic parameters. A 3 is appropriate because the schema carries most of the semantic load and the description provides only partial mapping.

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

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

The description uses a specific verb ('Runs') and clearly names the resource: a 90-day B2B revenue leakage and Visa CE 3.0 readiness audit. It also scopes the tool to caller-supplied Stripe subscriptions, usage events, and disputes. It does not explicitly differentiate itself from related sibling tools such as revclamp_stage_stripe_dispute_ce3 or revclamp_lint_dispute_evidence, 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?

The description gives no guidance on when to use this tool versus alternatives, nor does it state prerequisites or exclusions. The schema's 'demo' parameter hints at a sample-preview mode, but the description itself does not explain when to invoke the audit, when to avoid it, or how it relates to sibling audit/dispute tools.

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

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

With no annotations, the description carries the full burden. It does disclose useful behavioural facts: the computation compares a 0% take-rate against a contingency take-rate, and results are expressed in integer USD cents. However it does not state that the operation is a side-effect-free simulation (no writes, no external calls), nor does it explain the model assumptions behind ghost bleed or won-dispute inputs, which matter for trusting the output.

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

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

A single dense sentence with no filler, and the core purpose is front-loaded in the opening verb. It packs comparison basis, units, and the recommendation into one clause chain, which is efficient though slightly breathless for a calculation with four opaque inputs.

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

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

There is no output schema, and the description partially covers the return: monthly and annual savings plus a recommended tier. But for a four-parameter calculation with zero annotation and zero schema-description support, an agent still lacks the input semantics and the pricing model's assumptions needed to call it confidently with non-default values.

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

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

Schema description coverage is 0%, so the description must compensate and it largely does not: monthlyUsageEvents, monthlyGhostBleedUsd, and monthlyWonDisputeUsd are never mentioned, leaving the agent to guess units and role. The description also says contingency rates of '25%-30%' while the parameter allows 1–50, creating ambiguity about the meaningful range. The one genuine addition is the output unit (integer USD cents), which does not resolve the unclear input units (defaults such as 600 and 10000 look like dollars, not cents).

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: calculates monthly and annual B2B margin savings comparing flat 0% take-rate pricing against 25–30% contingency agencies, and recommends a tier. That is far more specific than any sibling (audit_revenue_leakage, evaluate_ghost_usage). The only soft spot is 'optimal tier', which is never defined and has no corresponding parameter, so an agent cannot tell what a tier is.

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 by the framing of the comparison — an agent can infer it is for pricing-model ROI evaluation rather than a sibling's audit/lint/validation job. There is no explicit when-to-use, no when-not-to-use, and no named alternative despite eight siblings that could plausibly be confused with a revenue-leakage calculation.

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

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

No annotations are provided, so the description must carry the full behavioral burden. It explains the conceptual evaluation but does not state whether the tool is read-only, what permissions or Stripe API access are required, how missing or malformed subscriptions are handled, or what the result contains.

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

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

The description is a single front-loaded sentence with no wasted text. The purpose and domain context are stated immediately, and the Stripe version qualifier is compact.

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 there are no annotations, no output schema, three parameters including two nested objects, and incomplete schema descriptions, the single sentence is not complete enough. It omits return-value behavior, dunning grace semantics, error conditions, and operational constraints.

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 only 67%, and the description adds no parameter-level meaning beyond the schema. It does not explain the dunningGracePeriodDays parameter at all, nor does it clarify the expected shape or handling of usageEvent and subscriptions beyond what the schema already says.

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

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

The description uses a specific verb, 'Evaluates whether,' and a precise resource: a metered API/SaaS usage event being entitled versus post-cancellation or post-grace ghost usage. It is clearly distinguishable from all listed sibling tools, which cover VAT validation, webhook verification, revenue leakage audits, ROI calculation, dispute linting, reconciliation, webhook replay, and dispute staging.

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 the usage context by framing the tool as determining whether a usage event is entitled or ghost usage. However, it gives no explicit when-to-use guidance, no exclusions, and no alternatives among the revclamp sibling tools.

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

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

With no annotations, the description carries the full disclosure burden; it does add useful traits ('non-destructive' block markers, merchant note preservation) suggesting a read-only, safe operation. But it never states the return shape (violations list? booleans?), whether it fails hard or reports findings, or how the preset/demo path differs.

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

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

A single dense sentence that front-loads the verb and resource and then enumerates the checks. No filler, though the bracketed notation and stacked clauses make it slightly hard to parse.

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 5-parameter tool with nested objects, zero annotations, and no output schema, the description should explain what lint results look like and what the demo/preset switches do. It covers the rule set well but leaves the input modes and output contract underspecified.

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 20%, so three of five parameters (accessActivityLog, priorTransactions, disputedTransaction) are undocumented in both places. The description implicitly ties accessActivityLog to the UTF-16 ceiling and the two-identifier overlap to the transaction objects, adding some meaning, but not enough to compensate for the coverage gap.

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

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

A specific verb ('Lints') plus a specific resource ('Stripe dispute evidence payloads') and the exact rules enforced (18,000 UTF-16 ceiling, CE 3.0 block markers, two-identifier overlap). This is clearly a validation tool, distinguishable from the sibling stage_stripe_dispute_ce3, though it never names that sibling or states the relationship.

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 says when to run this versus revclamp_stage_stripe_dispute_ce3, or whether it is a pre-flight gate before staging. The 'demo' and 'preset' parameters imply a sample/fixture path, but no guidance is given on when to use them.

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

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

With no annotations provided, the description carries the full burden. It does disclose meaningful behavioral context — integer EUR-cent arithmetic and double-entry accounting, implying exact, float-free, deterministic computation in a single currency — but it never states whether the tool is side-effect-free, whether it persists anything, or what the reconciliation result looks like.

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

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

A single front-loaded sentence that packs the domain, terms, and accounting model with no filler. It is dense but every clause carries information; only a slight readability cost from cramming many qualifiers into one sentence.

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

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

For a 7-parameter tool with no annotations and no output schema, the description is under-specified: the agent cannot tell what is returned (a status, a delta, a journal entry?), how overdue terms interact with daysElapsedSinceInvoice, or what the reconciliation outcome means. The return-side burden falls entirely on nothing since no output schema exists.

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

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

Schema description coverage is 0%, so the description must compensate and it partially does: credit notes, upfront deposits, payment terms (Net-15/30/60), order totals, and rounding tolerances all map to named parameters. However, daysElapsedSinceInvoice is never mentioned, and semantics such as what happens when the deposit is short or how toleranceCents changes the outcome are left unexplained.

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 ("Reconciles") and a precise resource domain (Shopify Plus B2B Net-15/30/60 wholesale invoices, deposits, credit notes, rounding tolerances). This is clearly distinct from the sibling tools (VAT validation, webhook signature, dispute linting, revenue-leakage audit), though it does not explicitly name or exclude 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 guidance on when to call this versus alternatives, no prerequisites (e.g., that Shopify Plus B2B orders are required), and no conditions under which it is inappropriate. The scope is implied by the description's subject matter 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?

With no annotations present, the description carries the full burden. It usefully discloses the core behavioral model — deduplication Set with a 72-hour window and a monotonic createdSec watermark compared against a naive handler — but says nothing about side effects (whether events actually hit an endpoint), return shape, or what 'simulate' produces. Meaningful but incomplete 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?

A single front-loaded sentence with no filler; the core mechanism comes first. The density of undisclosed jargon ('monotonic createdSec watermark') makes it slightly harder to parse than necessary, but nothing is 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?

No annotations, no output schema, no required parameters, and 0% schema description coverage mean the description is the only source of truth — yet it omits return values and the semantics of two of three parameters. For a simulation tool whose output is the whole point, this leaves significant gaps.

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

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

Schema coverage is 0% and all three parameters are undocumented. The description implies the 72-hour window that idempotencyWindowSec defaults to, but doesn't state the window is configurable, doesn't describe what the 'events' array items look like, and doesn't explain how scenarioPreset interacts with events (precedence or mutual exclusivity).

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 ('Simulates') and a precise resource (out-of-order/duplicate subscription lifecycle webhooks) plus the mechanism it tests (72-hour dedup Set, monotonic createdSec watermark, naive arrival-order baseline). This clearly separates it from the only webhook-adjacent sibling, revclamp_verify_webhook_signature, though it never names siblings 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 explicit when-to-use, when-not, or alternative-tool guidance. The phrase 'vs. a naive arrival-order handler' hints at a comparison/testing purpose but leaves the agent to infer when to pick this over other revclamp tools.

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

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the operation is non-destructive and limited to 18,000 UTF-16 code units, but it omits permissions, side effects, validation/error behavior, and return format. It also references 'submit: false' even though the input schema has no submit parameter and disallows additional properties.

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?

It is a single dense sentence that front-loads the core purpose and key draft/size constraints. There is no filler, although the compression hides important usage and parameter guidance.

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?

This is a complex 8-parameter, nested-object tool with no annotations and no output schema, so the description needs to do more. It covers the high-level purpose and draft limit but leaves parameter meanings, expected outputs, prerequisites, and failure modes largely unexplained.

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 only 13%, and the description does not explain the roles of disputeId, customerId, usageEvents, priorTransactions, disputedTransaction, existingAccessActivityLog, or disputeReason. Worse, it mentions a 'submit' flag that does not exist in the schema, which can mislead invocation.

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 specific operations: evaluating Visa CE 3.0 120d-365d footprint overlap and building a non-destructive access_activity_log draft. It is clear enough to distinguish this as a specialized dispute-evidence staging tool, but it does not name sibling tools or clarify how it differs from lint_dispute_evidence or evaluate_ghost_usage.

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 a staging/non-submitting use case via 'submit: false' and the demo parameter's schema note, but it never states when to use this tool versus alternatives. It also gives no prerequisites, exclusions, or routing guidance for the many sibling dispute-related tools.

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

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

No annotations are provided, so the description must disclose behavior. It states local checking and demo simulation, but it does not explain LIVE mode, external VIES calls, failure/error behavior, concurrency/rate limits suggested by GLOBAL_MAX_CONCURRENT_REQ, or whether the operation has side effects.

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

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

The description is a single front-loaded sentence with no filler, and the parentheticals carry useful constraints. It is dense but appropriately sized for a utility 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 four parameters, 25% schema description coverage, no annotations, and no output schema, the description needs to compensate for missing invocation details. It gives the core business rule but leaves viesMode selection, sellerCountry format, LIVE/network behavior, and return values undocumented, so it is not complete enough to call confidently.

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 only 25%; only demo has a schema description. The description implies buyerVatId is the VAT ID and sellerCountry drives cross-border eligibility and notes GR→EL, but it leaves sellerCountry's expected format and all viesMode enum semantics unexplained, especially FORMAT_ONLY versus LIVE.

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 operation: normalizing EU/XI B2B VAT IDs and checking cross-border reverse-charge format eligibility, including the GR→EL conversion. It is clear enough to separate this from the other revclamp tools, though it does not explicitly compare itself to any sibling.

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 implies the tool is for local format eligibility and says demo:true covers simulated VIES states, but it gives no explicit when-to-use/when-not guidance, prerequisites, or alternatives for the LIVE and FORMAT_ONLY modes. The agent must infer which viesMode to select.

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

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: raw-UTF8 encoding, the exact HMAC algorithm, per-provider header conventions, and a 300s timestamp replay-protection window. It stops short of the behaviors that matter most for a combined generate/verify tool - which mode is selected and when, and what a failed verification produces (error vs. boolean).

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 sentence, front-loaded with the verb, and every clause carries information an agent cannot get from the bare schema. No filler or restatement of the tool name.

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 six-parameter tool with no annotations and no output schema, the description leaves critical gaps: the return shape of a verification (boolean, parsed result, or thrown error) is unknown, and the role of signatureHeader in choosing generation versus verification is unstated. An agent could call it correctly on inputs but not predict its outcome.

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

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

Schema description coverage is 0% across six parameters, so the description must compensate and largely does not. It maps provider values to header formats and implies toleranceSec via the 300s window, but secret, rawPayload, timestampSec, and especially signatureHeader (which appears to be the generate-vs-verify switch) are never explained.

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 pair (generates and verifies) plus the resource (HMAC-SHA256 webhook signatures) and even enumerates the three supported providers with their header formats. What it does not do is differentiate this tool from the sibling revclamp_simulate_webhook_replay, which an agent could plausibly 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 statement of when to reach for this tool versus revclamp_simulate_webhook_replay or any other sibling, and no prerequisites are given (where the secret comes from, whether rawPayload must be the unparsed body). The provider/header breakdown hints at inbound webhook validation, but usage is left entirely to inference.

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