ClausePilot

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 useful protocol behavior: a $0.05 USDC charge and that a missing paymentSignature yields an x402 challenge to retry against. However, it says nothing about what the analysis returns, whether it is read-only, or any auth beyond payment, leaving real gaps for a paid tool.

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 payment cost and retry path front-loaded; little waste. It is a bit lopsided, spending its budget on payment mechanics rather than the analysis itself.

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 paid tool with no annotations and no output schema, the description is thin: it omits what the risk analysis produces and leaves four parameters undocumented. Only the payment mechanics are covered, so a caller still lacks what it needs to use the tool correctly beyond payment.

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 33% (text and paymentSignature). The description restates paymentSignature behavior already in the schema and adds nothing for owner, title, category, or counterparty, so it fails to compensate for the low coverage across the six parameters.

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 name says 'analyze_contract_risk' but the description only calls it 'contract workflow analysis', which is vague about what is actually analyzed or produced. It does not distinguish this tool from siblings like review_vendor_contract_risk or compare_contract_risk, which a caller must choose between. The verb+resource are present but underspecified.

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 explains the payment retry flow (omit paymentSignature, then retry), which is behavioral rather than selection guidance. It gives no indication of when to pick this tool over the many sibling contract analysis tools, and no exclusions are stated. Usage must be inferred.

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, but it does disclose a meaningful behavioral trait: this is a paid tool costing $0.04 USDC. That is genuinely useful for an agent deciding whether to invoke it. However, it says nothing about failure modes, what happens if no NDA clauses are found, or output 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?

A single sentence with no waste, and the pricing disclosure is appropriately front-loaded for a paid x402 tool. Slightly dense with the clause enumeration but each item earns its place by telegraphing scope.

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 no annotations, so the description should do more work. It partially compensates by listing the clause categories it returns, but omits output format, behavior on missing clauses, and any input length or document-type 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 100%, so all four parameters (text, title, counterparty, paymentSignature) are already documented in the schema. The description adds no parameter-level detail beyond what is structured, 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?

Names a specific verb (extracts) and resource (NDA clauses), then enumerates the exact clause types covered: confidentiality scope, duration, exclusions, residuals, return/destruction. This distinguishes it from broad siblings like analyze_contract_risk, though the differentiation is implied by the 'NDA' qualifier rather than stated.

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

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

No guidance on when to choose this over extract_contract_obligations or analyze_contract_risk, and no stated prerequisites beyond the implied need for contract text. The agent must infer applicability from the NDA-specific clause list 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, the description carries the full behavioral burden. It helpfully discloses that this is a paid tool at a specific price ($0.04 USDC), which is real behavioral information for a cost-sensitive agent, and implies an analysis/read operation. However, it omits confirmation that it is non-destructive/read-only, the output shape, and failure behavior if payment is not tendered.

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 puts cost and purpose first with no filler. It is efficient and well-ordered, though the trailing list of signal categories is broad enough to verge on enumeration for its own sake.

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 no-annotation, no-output-schema tool, the description establishes purpose and cost but says nothing about return structure or what the checked signals look like as output. Adequate to select the tool, thin for predicting its result.

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 of 3 applies. The description adds no parameter-level detail (no mention of text, title, counterparty, or the payment signature flow), leaving all semantics to the schema, which already documents each field adequately.

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 concrete verb (checks) and a specific resource domain (SaaS terms), then enumerates the signal categories it reports: suspension, unilateral changes, data, SLA, renewal, liability. This is clearly distinguishable from siblings such as check_nda_clauses or extract_payment_terms by domain and output intent, though the description never names an alternative to reinforce the distinction.

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

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

No guidance on when to choose this tool over check_nda_clauses, analyze_contract_risk, or review_vendor_contract_risk. The only usage-adjacent content is the payment flow, which is carried in the schema's paymentSignature description rather than here. An agent must infer the selection criteria 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?

With no annotations, the description carries the full burden. It usefully discloses the paid nature and exact price ($0.06 USDC), which is a real behavioral trait, but says nothing about latency, whether comparison is symmetric, or what the response contains. The payment handshake is left entirely to the schema's paymentSignature description.

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 sentence with no filler, and the cost/payment gate is front-loaded before the purpose clause. Efficient, though the cost-first ordering slightly buries what the tool actually does.

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 no annotations, so the description should describe what the comparison returns (structure, verdicts, scoring). It names the risk dimensions but not the output shape, leaving a gap for a paid tool with a non-trivial result.

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 textA/textB, the optional titles, and the x402 paymentSignature flow. The description adds no format or size guidance for the contract inputs, 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 ('compares') and resource ('two contracts') and enumerates the comparison dimensions (renewal, notice, penalties, operational risk). The two-contract scope implicitly differentiates it from single-contract siblings like analyze_contract_risk, but no sibling is named 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?

No guidance on when to pick this over analyze_contract_risk, review_vendor_contract_risk, or the other analysis siblings, and no exclusions or prerequisites beyond the implied payment. The cost mention hints at a gating condition but is not framed as 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?

No annotations are provided, so the description carries the full burden. It does disclose the meaningful behavioral fact that this is a paid tool ($0.02 USDC), which is non-obvious and actionable. However, it says nothing about return format, determinism, or failure behavior, leaving a gap for an un-annotated tool.

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

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

A single compact sentence with the cost front-loaded and the capability immediately after. No wasted words, though it is on the terse side for a paid analysis 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?

There is no output schema, but the description implies the return content (extracted operational obligations) and the pricing model, and the payment handshake is covered by the schema. Only the shape/granularity of the extracted obligations remains unspecified, which 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 the baseline is 3. The description adds no parameter-level detail beyond what the schema already documents (text, title, counterparty, paymentSignature and its challenge/retry flow).

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 ('extracts') plus resource ('operational obligations') and an enumeration of the covered categories (reporting, security, SLA, audit, insurance). This distinguishes it from the other extract_* siblings (payment terms, employment terms, renewal deadline), so an agent can route without opening schemas.

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 statement of when to use this versus alternatives such as extract_payment_terms or check_nda_clauses, and no prerequisites beyond the pricing mention. Usage must be inferred from the tool name and obligation category 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?

With no annotations, the description carries the full burden and does disclose two useful traits: it is a paid tool at $0.04 USDC and it stops short of jurisdiction-specific legal conclusions. However, it says nothing about return format, idempotency, or how the x402 payment flow behaves beyond what the schema already states.

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 the cost first and the scope caveat second; nothing is wasted. It is efficient, though it could carry slightly more substance for a paid 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?

No output schema exists, so the description is the only place to explain what the extraction returns, and it does not. It covers the paid nature and the legal-conclusion boundary but leaves the shape of the result and the payment retry flow to the schema.

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

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

Schema description coverage is 100%, so all four parameters including the required 'text' and the paymentSignature flow are already documented in the schema. The description adds no parameter-level 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?

States a specific verb+resource ('extracts employment terms') and adds a meaningful scope boundary ('without making jurisdiction-specific legal conclusions'). The resource is distinct enough from siblings like extract_payment_terms or extract_renewal_deadline, though no sibling is named 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?

No guidance on when to use this versus the many alternative extraction and analysis tools (analyze_contract_risk, extract_contract_obligations, etc.). Usage is only implied by the resource name; no conditions, prerequisites, or exclusions are given.

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

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

With no annotations, the description carries the full behavioral burden. It discloses that the tool costs $0.02 USDC, but does not state that it is a read-only extraction, whether it has side effects, permission requirements, or rate limits. The schema parameter paymentSignature partially documents the payment flow, so the description adds little beyond cost.

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 efficient sentence that front-loads the pricing and then lists extraction targets. No wasted words, though it could be slightly more structured to separate cost from capability.

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 output schema exists, and the description lists the categories of extracted signals, which partially compensates by indicating what the output contains. However, it does not describe the return format (e.g., structured JSON vs. free text), error handling, or payment retry behavior beyond what the schema parameter implies.

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 (text, title, counterparty, paymentSignature) are already documented. The description adds no parameter-level detail such as expected text format or optionality assumptions, so 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 states a specific verb and resource: it extracts payment-related signals (timing, invoicing, late fees, currency, billing cycle, discounts) from contract text. The field list distinguishes it from generic siblings like extract_contract_obligations, though it does not explicitly name an 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 guidance on when to use this tool versus siblings such as extract_contract_obligations, check_saas_terms, or get_clausepilot_payment_info. The mention of being a paid tool gives cost context but no routing or exclusion rules.

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 add one genuinely useful behavioral fact: the tool is paid ($0.015 USDC), plus the schema hints at the x402 payment flow. It omits return shape, precision/confidence, and whether the extraction is deterministic, so it is partial rather than thorough.

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 well-formed sentence that front-loads the cost and then the extracted signals. No filler or redundancy, though the price leading the sentence slightly buries the core purpose.

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 and no annotations, the description should ideally say what the result looks like and how to interpret missing signals, but it stops at listing the signal types. It is adequate for invocation but leaves return-format and reliability questions unanswered.

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 the schema already documents all four parameters including the x402 paymentSignature retry flow. The description adds no parameter-level meaning beyond that, 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 states a specific verb ('extracts') and enumerates the exact signals returned (term, expiry, auto-renewal, notice-window) from contract text, which is more informative than the name alone. However, it does not distinguish itself from siblings like extract_contract_obligations or extract_payment_terms, so an agent still has to infer boundaries.

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 use this tool versus the many sibling extraction tools, nor any exclusion or prerequisite beyond the implicit 'contract text' input. The only guidance is the implied price signal, which tells the agent it costs money but not when it is the right choice.

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

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that this is a paid tool costing $0.015 USDC, which is real information beyond the schema. However, it says nothing about the payment flow, that the operation is read-only/non-destructive, or rate limits, leaving meaningful behavioral gaps.

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

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

A single tight sentence with no filler, though it leads with the price rather than the tool's function. Every clause earns its place and nothing is redundant.

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 annotations and no output schema, the description is adequate but thin: it identifies the target concepts but not the shape of the result or any caveats. The schema covers the payment signature mechanism, so the main gap is around what the analysis returns and when it is preferable to 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%, with each parameter documented (including the x402 paymentSignature flow), so the schema already does the heavy lifting. The description adds no parameter-level detail beyond what the schema provides, making the baseline 3 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 (finds) plus the resource (early termination fees, liquidated damages, late fees) and even enumerates the exposure types it targets, so an agent knows what it returns. It does not explicitly differentiate itself from siblings like extract_payment_terms, but the enumeration is distinctive enough to infer scope.

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 reference to any alternative tool, despite a crowded sibling set (check_nda_clauses, extract_contract_obligations, etc.). The only usage-adjacent signal is the price and the word 'finds', which implies analysis but not 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?

No annotations are provided, so the description carries the full burden. It does disclose the key behavioural fact that the call is free ('without charging') and that it exposes x402 payment protocol details, but says nothing about authentication, rate limits, or whether the returned URL/price can change. Adequate but thin for an annotation-free tool.

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 packs the four return fields plus the no-charge guarantee with no filler.

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

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

For a zero-parameter read-only lookup with no output schema, the description usefully enumerates the returned fields (URL, price, network, payment protocol) and the pricing guarantee. It could still say more about output shape or freshness, but 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?

The tool takes zero parameters, so per the rubric the baseline is 4. The schema is empty and there is nothing for the description to clarify or compensate for.

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?

Uses a specific verb (Returns) with a named resource (ClausePilot flagship paid contract-risk API URL, price, network, x402 payment protocol), and enumerates what comes back. An agent can distinguish it from siblings like list_clausepilot_paid_tools or analyze_contract_risk purely from the description.

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 phrase 'without charging' implies this is the free metadata/discovery call an agent should make before touching a paid tool, but the description never states when to use it versus list_clausepilot_paid_tools or why an agent would call it. Usage is implied, not explicit.

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

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

With no annotations, the description carries the behavioral burden and does disclose a meaningful trait: the call is free ("without charging") and returns price/endpoint metadata. For a zero-parameter catalog tool this adequately covers the key behavioral fact, though it says nothing about output format or limits.

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 wasted words; the verb and scope lead, and the notable "without charging" qualifier closes it.

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 0-param, no-output-schema list tool, the description covers what is returned (price and endpoint) and the key cost behavior. Slightly more on how it relates to the paid-tool flow would make it complete, but 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?

The tool takes zero parameters, so the schema-baseline of 4 applies. There is nothing for the description to clarify about inputs.

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 ("Lists") and a clear resource set ("flagship API plus all focused Agent Store tools"), and adds what each entry contains (price and endpoint). This distinguishes it from the analysis-oriented siblings, though the terminology ("flagship API", "Agent Store tools") is somewhat jargon-heavy.

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 phrase "without charging" hints at when to use it (to preview pricing before invoking paid tools), but the description never explicitly says to prefer this over the sibling get_clausepilot_payment_info or when it is required. Usage is implied rather than 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?

With no annotations, the description carries the full burden. It usefully discloses that the tool is paid ($0.05 USDC), a real behavioral trait beyond the schema, and paymentSignature in the schema explains the x402 challenge-then-retry flow. However it says nothing about what the review returns, depth of analysis, or limits on contract size.

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 sentence, front-loaded with the payment constraint before the purpose. Efficient, though the enumerated risk list is somewhat long without adding routing value.

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 4-parameter paid tool with no annotations and no output schema, the description covers cost and scope but omits return-shape expectations and any indication of analysis depth. Adequate but with clear gaps an agent would want filled before calling.

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 text, title, counterparty and paymentSignature. The description adds no syntax or format detail for these parameters, 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 (reviews) and resource (vendor contracts) plus an enumerated scope of risk signals (renewal, lock-in, service, data, liability, commercial). This is clear enough to distinguish from extraction siblings, but it never differentiates itself from the close cousins analyze_contract_risk or compare_contract_risk.

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 mention of alternatives, despite siblings like analyze_contract_risk and compare_contract_risk doing overlapping work. The agent must infer from the name alone whether this is the right risk tool to call.

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

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

No annotations are provided, so the description carries the full burden. It usefully discloses that the operation is paid ($12.90 USDC) and high-volume, which is real behavioral context, but it omits payment failure behavior, whether charges are reversible, and rate or capacity failure modes beyond the cap.

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 purpose, price, capacity, and output type without waste. It could be marginally tighter, but every clause earns its place.

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

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

With no output schema and no annotations, the description should do more to describe the ranked triage result and the paid-flow consequences, especially since real money is involved. The schema covers the x402 payment challenge mechanics, but the agent still lacks a clear picture of cost-of-failure and result shape.

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 only 50%: the paymentSignature parameter is documented inline in the schema, but the contracts array-level semantics are not. The description adds the 'up to 200' capacity bound and the payment context but does not explain the nested contract object fields or what qualifies as valid input beyond what the schema already states.

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 (scan) and resource (contract portfolio) and states the capacity cap and the ranked operational triage output. It is clear what the tool does, though it differentiates from the scan_contract_portfolio_50 sibling only implicitly via the '200' in the name rather than through an explicit comparison.

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 choose this tool over scan_contract_portfolio_50, triage_contract_batch_10, or the single-contract triage tools. The word 'high-volume' hints at scale but never states the selection condition or any exclusivity, leaving the agent to infer usage 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?

With no annotations, the description carries the full burden, and it does disclose the key behavioral fact that this is a paid operation at $3.49 USDC plus the 50-contract ceiling. It omits whether payment is still consumed on partial failure, retry/idempotency behavior, and latency for a 50-document batch.

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 sentence that front-loads the two decision-critical facts: the price and the 50-contract scope, followed by the output content. No filler whatsoever.

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 and no annotations, the description usefully enumerates the returned summary types (ranked risk, renewal, penalty, obligation, payment terms) and the price. Only the payment lifecycle and batch failure semantics are left unaddressed, which the schema partially covers.

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 50% and the description adds no parameter detail beyond the implicit 50-item cap already enforced by maxItems. The paymentSignature challenge-then-retry flow is documented in the schema, not the description, so the description neither compensates for nor duplicates 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?

States a specific verb (scan) and resource (contract portfolio) with an explicit scope cap of 50 contracts and a named price. It clearly distinguishes itself from single-contract siblings like analyze_contract_risk, but it never names scan_contract_portfolio_200 as the alternative for larger portfolios.

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: nothing says when a portfolio-level scan beats individual calls to triage_contract or extract_contract_obligations, and no condition selects this tool over the 200-contract variant. The price is stated, but no prerequisite or eligibility context is given.

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

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

With no annotations at all, the description must carry the behavioral burden. It helpfully discloses the paid model ($0.02 USDC), which is material for an agent budget, but it does not state that the operation is non-destructive/read-only, nor any failure, timeout, or length-limit behavior.

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 sentence that front-loads the two facts an agent most needs: the cost and the output being a compact structured summary. No filler.

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

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

There is no output schema and no annotations, so the description should sketch the return shape and safety profile more than 'compact structured summary' does. The payment mechanics are covered by the schema, but the result contract remains underspecified for a downstream-agent-facing 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%, including the paymentSignature retry flow, so the schema already documents all four parameters. The description adds no syntax or format meaning beyond that, 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 ('produces a compact structured contract summary') and resource, which sets it apart from the sibling extract_* and check_* tools. However, it never names a sibling or clarifies the summary's boundary against analyze_contract_risk or extract_contract_obligations.

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 phrase 'for downstream agents and workflows' vaguely implies a use case, but there is no when-to-use guidance, no exclusions, and no routing among the eleven sibling contract tools. An agent cannot tell from this text when summary is preferable to extraction or risk analysis.

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 usefully discloses the price ($0.08 USDC) and that this is a paid bundle, and the schema covers the x402 payment challenge flow via paymentSignature. However, it says nothing about latency, whether the call is read-only, or what happens on insufficient payment beyond what the schema field already states.

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 sentence that front-loads the cost and then the output set; every clause earns its place. Slightly awkward phrasing ('Paid $0.08 USDC bundle') but no waste or redundancy.

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

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

There is no output schema, so the description must enumerate return values — and it does, listing five concrete outputs. Combined with the schema's paymentSignature guidance, an agent has enough to invoke correctly, though return format and pagination/limits remain unspecified.

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 (text, title, counterparty, paymentSignature) are already documented, including the omit-then-retry payment dance. The description adds no parameter-level meaning, 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 concrete resource (contract analysis) and enumerates the five specific outputs it bundles (summary, renewal timing, penalties, obligations, payment terms). This distinguishes it from the narrower siblings like extract_contract_obligations or find_contract_penalties, though it never explicitly frames itself as the bundle alternative to those tools.

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

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

The phrase 'in one call' implies the intended use case is consolidating what four sibling extraction tools would do separately, but no when-to-use or when-not-to-use condition is stated. An agent must infer the routing decision from the output list 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, the description carries full behavioral burden. It usefully discloses the $0.69 USDC cost and that payment is required, but says nothing about what triage actually evaluates, whether the operation is read-only, what the ranking basis is, or how failures on individual contracts are handled.

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

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

A single compact sentence that front-loads the price and the batch size. No filler, though the compressed phrasing sacrifices clarity for brevity.

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 output schema and no annotations, yet the description does not explain the triage output, the ranking mechanism, or the two-step payment handshake. For a paid batch tool touching up to 10 contracts, this leaves major questions unanswered.

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 only 50%, and the description adds no parameter meaning beyond the schema. It does not clarify aggregate behavior across the contracts array or reinforce the note that paymentSignature should be omitted first to receive the challenge.

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 verb (triage) and resource (contracts) with a batch limit of 10, which is somewhat specific. However, 'portfolio tool' and 'portfolio-level ranking' remain vague, and it does not distinguish itself from siblings like triage_contract, triage_pdf_contract, or scan_contract_portfolio_50 that occupy the same space.

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

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

No guidance on when to use this batch variant versus the single-contract triage_contract or the larger scan_contract_portfolio tools. The batched nature is implied only by the name and the '10 contracts' phrase, leaving the agent to infer 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?

With no annotations, the description carries the full behavioral burden and does add real value: the $0.12 USDC cost, the rejection-before-settlement guarantee, the 30-page extraction limit, and the text-based requirement. It falls short on output shape, describing the return only as 'bundled contract triage.'

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 dense sentences, front-loaded with the paid nature and input constraint, then the extraction scope and rejection behavior. No filler.

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

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

There is no output schema, so the description should characterize the returned triage payload; 'bundled contract triage' is too vague to tell an agent what fields or verdicts come back. Input limits and payment behavior are otherwise well covered.

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

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

Schema description coverage is 100%, so both required and optional parameters (pdfBase64, title, counterparty, paymentSignature) are already documented, including the x402 retry flow. The description adds no parameter-level 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?

The description gives a specific verb and resource: extracts up to 30 pages and returns contract triage for text-based PDFs. It clearly separates itself from the text-based sibling triage_contract by scoping to PDFs, though it never names that sibling or the other analyze/extract tools.

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

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

Usage constraints are implied rather than spelled out: text-based PDFs only, image-only PDFs rejected, 30-page cap. There is no explicit statement of when to pick this over triage_contract or the extract_* siblings, so the agent must infer routing.

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