Tereno on Base

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

With no annotations, the description carries the full burden and does substantial work: it discloses the $0.25 USDC x402 charge on Base, the no-cache/no-share/no-resale privacy posture, and two explicit non-guarantees (no inclusion prediction, no MEV protection). It is silent on failure modes, e.g. what happens when the router is unsupported or the calldata cannot be decoded.

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 question, then the mechanics, then limits/cost. Dense but each sentence carries new information; no filler or repetition of the title.

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 9-parameter tool with zero required params, two mutually exclusive invocation paths, and no output schema, the description never explains what "bounded evidence" actually contains or how a caller should choose between calldata and tokenIn/amountIn/tokenOut. The dual-path guidance gap and undefined return shape leave real ambiguity.

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 explains every parameter including the "alternative to data" dual invocation path. The description only adds the notion that the encoded constraint is decoded (min-output vs max-input), which overlaps with minAmountOut/amountIn rather than extending them.

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 chain (recognize routers, simulate the unsigned Base transaction, decode min-output/max-input constraint) on a specific resource (a prepared Aerodrome swap), and the title frames it as a pre-signing check. It is clearly distinguishable from sibling guards such as uniswap_v4_hook_guard or transaction_intent_guard.

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?

"before signing" plus the explicit exclusions ("Does not predict inclusion or protect against MEV") establish when the tool is and is not the right choice. However, no alternative tool is named, so an agent must infer that other guards exist for other scenarios.

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 transparency. It discloses a key behavioral trait: cost sharing/reuse where answers cached by other agents reduce cost and earn credit for the producing wallet. This goes beyond simple read behavior and aids expectation setting.

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

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

The description is three sentences, front-loaded with the core purpose and supported by pricing and reuse details. It is not overly verbose, though the cost explanation could be shortened without losing clarity.

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 no parameters and no output schema, the description adequately explains what the tool returns and the pricing model. It is complete enough for an agent to understand the tool's purpose and operational context, though it lacks explicit return format or error handling.

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

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

The input schema has zero parameters and is fully covered (100%). The description clarifies that no parameters are required and adds meaning by listing the returned data fields, which is useful since no output schema is provided.

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

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

The description clearly states the tool retrieves the current state of Base, listing specific data points (latest block number, timestamp, base fee, suggested gas fees) and emphasizes it requires no parameters. This distinguishes it from sibling tools that deal with contracts, evidence, and transactions.

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

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

The description provides context on when to use the tool (getting current state cheaply) and the cost model, but does not explicitly contrast with sibling tools or state when not to use it. An agent must infer exclusivity from the sibling names.

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 discloses several non-obvious behaviors: the paid-per-call model with x402, pricing based on network caching, sharing mechanics, and that each answer includes the block at which it becomes invalid. It does not mention edge cases like what happens if there is no previous observation, but the disclosure is substantial.

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

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

The description is concise and information-dense, covering purpose, examples, output, cost, and sharing in four sentences. It is front-loaded with the core purpose and avoids redundancy, though the opening question is largely rhetorical and could be trimmed.

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 tool's simplicity (one parameter, no output schema), the description covers the key aspects: what it does, when to use it, what output to expect, and the business model. It lacks explicit failure/edge-case behavior, but for its complexity it is well-rounded and complete.

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

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

Schema description coverage is 100% and the schema itself already provides a detailed description of the 'address' parameter, including its pattern and use case. The tool description reinforces that it refers to a 'Base contract' but adds little beyond the schema, so the baseline of 3 is appropriate.

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

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

The description clearly states the tool's function: comparing a Base contract with its previous Tereno observation to detect changes such as proxy upgrades, admin swaps, bytecode changes, or pauses. It uses a specific verb ('compare') and resource ('Base contract', 'Tereno observation'), and the examples of detectable changes distinguish it from sibling tools like contract_guard or contract_interface.

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

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

The description provides clear usage context by suggesting 'Poll it on a watchlist' and enumerating specific scenarios (silent proxy upgrade, admin swap, etc.). However, it does not explicitly mention when not to use this tool or name alternative tools, so it falls short of the highest mark.

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 a genuinely non-obvious trait: the x402 per-call payment model, a $0.02–$0.1 USDC cost range tied to network answer availability, and cache-sharing economics including producer credits. It is silent on what the 'bounded action verdict' actually contains, failure modes, and any auth/latency behavior, so the operational picture is incomplete.

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 capability is front-loaded in the first sentence, which is good structure. The payment and shared-cache sentences are dense but partly promotional, and some of that detail could be trimmed without losing decision-relevant 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?

There is no output schema and no annotations, so the description is the only source of return-shape information – yet 'bounded action verdict' is never defined in terms of possible outcomes. It lists what is inspected (executable code, proxy signals, pause signals) but leaves the agent unsure how to interpret or act on the 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?

One parameter with full schema description coverage, so the schema already explains that it is a Base contract address matching a hex pattern. The description adds nothing beyond the schema here; 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 uses a specific verb and resource: checks whether an address is executable code, detects proxy and pause signals, and returns a bounded action verdict. That is far more than a restatement of the name. It does not, however, distinguish itself from close siblings like contract_change, contract_interface, or transaction_intent_guard, so an agent gets no routing help.

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 implied by the framing question 'Is this Base contract safe to interact with?', which suggests calling it before interacting with an unknown contract. There is no explicit when-to-use, when-not-to-use, or named alternative among the many contract-oriented siblings, so the agent must infer the trigger.

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 discloses cost, sharing, bounded check, and credit mechanism, contributing valuable behavioral context. It doesn't mention read-only nature or return format, but the cost and sharing details exceed typical descriptions.

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

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

Three sentences with front-loaded purpose and efficient details. Every sentence adds value, including cost and sharing, without 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?

The tool has one parameter, no output schema, and no annotations. The description covers purpose, detection scope, and cost model, but doesn't describe the return format or error behavior. Given the complexity, it's reasonably complete but with notable 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 100% with a well-described address parameter. The description doesn't add any syntax or semantics 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 clearly states the tool detects ERC-20, ERC-721, ERC-1155, ERC-165, and EIP-1967 proxy slots in one bounded check, which is a specific verb+resource. The title reinforces the purpose and distinguishes it from siblings like token_metadata or contract_change.

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 usage (detect contract standard) but lacks explicit alternatives or when-not-to-use guidance. It provides clear context around the tool's function and cost model, but no comparison to 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 disclosure burden. It reveals key traits: no immediate credit, bounded and non-transferable credit, and conditional release only if the same wallet later settles the capability. This is useful, though it doesn't mention if the pledge is irreversible or if it has other 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 two sentences, front-loaded with 'Free market-signal pledge,' and every clause adds value. It is concise without sacrificing key behavioral 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 tool with only two well-documented parameters and no output schema, the description provides sufficient context about the pledge's purpose and credit behavior. It lacks guidance on return values or failure conditions, but these are less critical for a simple declarative 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 coverage is 100% for both parameters, so the schema already documents wallet and capability thoroughly. The description adds some context (e.g., 'same wallet' reinforces the wallet parameter) but doesn't provide additional syntax or format details beyond the schema, warranting a baseline score.

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

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

The description clearly states it is a market-signal pledge for declaring a capability you would pay for, with a specific conditional credit mechanism. This distinguishes it from sibling tools like chain_snapshot or token_metadata, which have different purposes.

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 does not explicitly state when to use this tool or when to avoid it. It implies a usage for signaling demand but offers no guidance on alternatives or exclusions, leaving 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?

With no annotations, the description alone communicates cost (paid per call, $0.01-$0.03 USDC), privacy (never cached/shared/resold), and scope (only public work). This adds transparency beyond a simple description, but it does not mention side effects, idempotency, or error behavior. It does not contradict any 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 reasonably concise, using four short sentences to convey purpose, return payload, cost, and privacy. It is front-loaded with the primary question and function, but includes some operational details (cost, privacy) that could be considered secondary. Still, each sentence adds value; no fluff.

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 partially compensates by listing the types of returned data (provenance, field validity, recomputation inputs), but it does not specify the response format (e.g., JSON structure). It also leaves the notion of 'reuse' and the decision threshold to inference. Complete enough for a simple tool but with gaps in expected output structure.

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 schema fully documents the only parameter (artifactId) with pattern and description, including expiration recomputation behavior. The main description adds no additional parameter-specific semantics beyond what the schema already provides. Baseline 3 is appropriate given 100% schema coverage.

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

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

The description clearly states the tool's function: to determine if a public Tereno artifact can be reused and return provenance, field validity, and recomputation inputs. It distinguishes itself from sibling tools by focusing on reuse eligibility for a single Base artifact with x402 payment.

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 does not provide explicit when-to-use guidance or alternative tool comparisons. While the question 'Can this public Tereno artifact be reused?' implies a usage scenario, there is no explicit statement about when to choose this tool over siblings like tereno_catalog or tereno_evidence_reference. It lacks exclusions or situational 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?

With no annotations present, the description carries the full burden, and it does add real value: it discloses the paywall ($0.75 USDC per call via x402 on Base), the privacy posture (never cached, shared, or resold), and that the tool simulates rather than executes, implying a read-only, non-mutating operation. It does not state failure modes, latency, or what happens if the market/oracle is stale despite claiming to check freshness.

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 body is compact and the operational steps are front-loaded, but the entire first sentence restates the title verbatim, which is pure duplication and delays the substantive content. Roughly a third of the text is redundant with structured metadata.

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 explain what the agent receives back (a boolean verdict, a health-factor value, an oracle-freshness flag), and it does not. For a decision-support guard tool that is exactly the missing piece; the paywall and privacy details are useful but do not close that 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 schema already documents all five parameters, including the optional borrowAmountWei. The description mentions a 'borrow/leverage action' but adds no syntactic or semantic 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?

The description gives a concrete verb-and-resource: simulate the user position against declared LLTV, evaluate the health-factor buffer, and check oracle freshness. It is protocol-specific (Morpho), which separates it from sibling guards like uniswap_v4_hook_guard or aerodrome_swap_guard. It does not, however, explicitly contrast itself with the many other *_guard tools beyond the protocol name.

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 'before execution' implies this is a pre-flight check to run prior to a borrow/leverage action, which is reasonable usage guidance. There is no explicit statement of when NOT to use it, nor any named alternative among the sibling guards, so the guidance stays at the implied level.

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

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

With no annotations provided, the description carries the full behavioral burden and handles it well: it discloses that the verdict is recomputed, that it includes supporting data, that it flags non-decision-grade verdicts, that it is paid per call via x402, and that responses are private and never cached. This goes well beyond a basic verb phrase and gives the agent realistic expectations for side effects, cost, and privacy.

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 dense but every sentence earns its place: purpose and return contents come first, followed by behavioral boundaries, pricing, and privacy. No wasted words or redundant restatements of the title or schema are present.

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?

Despite having no output schema, the description explains the key return elements (receipt bytes, challenge count, inputs) and the decision-grade behavior, and the input schema covers obligationId thoroughly. The only minor gap is the absence of a precise output field structure or error-handling expectations, but for a simple one-parameter tool the description is sufficiently complete.

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

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

Schema description coverage is 100%, and the schema already provides strong semantics for obligationId, including its source, format, and the decisionGrade caveat. The tool description complements the output semantics but does not add new meaning about the parameter itself, so the baseline score of 3 is appropriate.

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

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

The description clearly states a specific action: 'Return a recomputed verdict on a published Tereno obligation' and enumerates the included outputs: receipt bytes, challenge count, and inputs to reproduce the verdict. It also distinguishes itself from escrow, custody, and settlement operations, making its role as a pure verdict product unambiguous relative to siblings.

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 establishes clear context: it is for checking whether an economic condition was satisfied on a published obligation, with obligationId sourced from tereno_find_claims. It also states exclusions ('No escrow, no custody, no settlement'), which helps an agent avoid misusing it for other Tereno operations, though it does not explicitly name alternative 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 burden and delivers meaningful operational detail: paid per call via x402 on Base at $0.15–$0.5 USDC, price varying with network knowledge, cache reuse costing less, and bounded credit to the producing wallet. This is rich cost/economic behavior rarely captured by annotations; it does not, however, describe the shape or format of the returned answer.

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 question and then the evaluation factors and payment terms. Efficient, though the opening echoes the title verbatim rather than adding new framing.

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?

Covers what is evaluated, the chains in scope, and the payment/sharing model, which is enough for an agent to decide to call it. Because there is no output schema, the description could say more about what the answer looks like, but the question framing makes the expected verdict reasonably clear.

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

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

Schema description coverage is 100%, so the schema already documents both symbol and address (including the 0x address pattern). The description only implies that the token is identified by these inputs and adds no format or precedence guidance, 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 second sentence gives a specific subject: evaluating 24/7 on-chain trading state against TradFi US market hours, oracle basis/staleness, corporate actions, and pause states for Robinhood Chain / EVM. That, plus the RWA/stock focus, distinguishes it from generic guards like contract_guard or swap_guard. The purpose is framed as a question rather than a verb-first statement, but 'Evaluate' makes the action 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?

Domain scoping (tokenized RWA/stock on Robinhood Chain / EVM) implies when it applies, but there is no explicit when-to-use, when-not, or named alternative among siblings such as contract_guard or aerodrome_swap_guard. Usage is left to inference from the domain.

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 present, so the description alone must carry the behavioral burden. It does so by stating that the catalog is free, that proposed capabilities are not built or sold, and that naming one at the demand-pledges endpoint is how future prerequisites are chosen. This preempts assumptions about what the catalog can provide or charge for.

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 tight three sentences that front-lod the purpose and value ('Free. Full capability catalog...'), then gives the only important before-action, and then clarifies a potentially confusing section. Every sentence contributes useful context, 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, no-output-schema catalog tool, the description is complete: it names what data will be found (answers, prices, validity, slar change/private), explains that the catalog is free, and handles the 'proposed' exception. There are no unexpected params, return fields, absent pagination, or auth requirements left unclear enough to matter.

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 schema has zero properties and complete schema description coverage (100%), so by the baseline, params need no additional explanation. The description adds no parameter detail, but none is necessary for a parameterless catalog tool.

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

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

The description clearly identifies this as the complete capability catalog for Tereno: what each capability answers, price tiers in USDC on Base, answer validity, and sharing status. It also explains that the proposed section represents unbuilt capabilities and routes those requests to a specific POST endpoint, which distinguishes this catalog from indirect siblings.

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 contains explicit guidance: 'Read this before paying for anything,' and explains that proposing an unnamed capability is done via POST /api/v1/demand-pledges. This tells an agent exactly when to consult the catalog first and seeds them away from treating proposed items as purchasable features.

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 proactively discloses that the tool is free, that installationId is hashed and deduplicated daily, and that it never creates payment or credit. This addresses the main behavioral concerns, though it does not exhaustively describe all behaviors such as error handling or side effects beyond logging.

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 concise sentences. The first states the core purpose and output; the second explains the optional parameter. It is front-loaded, contains no filler, and every clause adds 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?

Despite having no output schema, the description explicitly enumerates what the tool returns (producer, validity window, normalized input). It covers the input (artifactId, installationId) and the operational context (experiment participation, no cost). For a simple read tool with one required parameter, this is fully complete.

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

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

The schema already provides 100% coverage of parameter descriptions, giving a baseline of 3. The description adds meaningful context beyond the schema, particularly for installationId (purpose of participating in the cross-agent experiment and its hashed/deduped handling) and artifactId (origin from another agent). This raises the score above the baseline.

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 'Resolve' with a clear resource (artifactId) and explicitly lists the output: producer, validity window, and normalized input. It distinguishes itself from siblings by specifying the use case 'another agent handed you', making its purpose unmistakable.

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

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

The description provides clear context for when to use the tool (when another agent hands you an artifactId) but does not explicitly mention alternatives or when not to use it. The context is strong, but it lacks explicit exclusions or other sibling tool references.

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 fully carries the behavioral burden. It discloses that the tool is free, that rewards are paid by the opener (not Tereno), that the reward is not escrowed, and that challenging is free at the claim's challengeEndpoint. This is rich, honest behavioral context that goes far beyond a simple read/list operation.

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

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

The description is three short sentences, each carrying distinct information: cost, scope, and challenge mechanics. It front-loads the 'Free' fact and stays fully on-topic 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 list tool with no output schema, the description thoroughly covers what claims are, how they are falsified, deadlines, reward source, and the challenge endpoint. This is complete enough for an agent to understand the tool's purpose and constraints without additional documentation.

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 single parameter 'limit' is fully described in the schema (100% coverage), so the description does not need to add parameter details. It contributes nothing beyond the schema, which meets the baseline for high schema coverage.

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 ('Lists') and a clear resource ('open, deterministic claims about Base proxy contracts'), with additional context about rewards and falsification. This clearly differentiates it from sibling tools like tereno_publish or tereno_catalog.

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 when to use the tool (to find claims you could challenge) and provides context (free, open), but it does not explicitly state when not to use it or name alternative tools. Since no exclusions or alternatives are given, it earns a mid-range score.

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 burden of behavioral disclosure. It states the tool is free, non-binding, does not reveal a wallet, and explains the hit/partial/miss tier semantics. This covers the essential behavioral traits for a pricing tool, though rate limits or auth are not mentioned.

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

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

The description is concise and well-structured: four short sentences, each adding meaningful information—cost, purpose, tier semantics, and value interpretation. No fluff or repetition.

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

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

The description comprehensively explains the return tiers (hit/partial/miss) without an output schema, and covers the tool's purpose and safety. Minor gaps exist around error handling or invalid inputs, but for a simple pricing tool, the description is sufficiently complete.

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

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

The input schema has 100% coverage, describing all four parameters with types and formats. The description adds little beyond 'one specific input,' so the schema already provides the necessary parameter semantics.

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

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

The description clearly states the tool's purpose: it provides an indicative price and reuse tier for a specific input, distinguishing it from sibling tools that perform actual operations. The title reinforces this as a cost-check tool.

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 usage before committing to an operation, but it does not explicitly state when to use this tool versus alternatives. No exclusions or alternative tool mentions are provided.

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 fully carries the behavioral disclosure burden. It explains costs (free, no gas), consequences (mismatch burns, match pays dividends), requirements (owning an agentId), and side effects (reputation registry projection). It also notes that unverifiable agentId claims are skipped without affecting the publication.

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 dense paragraph with six sentences. It front-loads key information (free, no gas) and every sentence contributes useful context. It is not overly verbose, though structured formatting could improve scanability.

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

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

The description comprehensively covers the tool's effects and prerequisites: burn on mismatch, dividend on match, reputation projection with agentId, and the external registration process. Despite lacking an output schema, it provides a complete picture of what happens before, during, and after the call.

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 baseline is 3. The description adds some context for agentId (audit projection) and the registration flow, but it largely repeats schema information. It does not significantly elaborate on computedAtBlock or bytecodeBytes beyond their existing schema descriptions.

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

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

The description and title clearly state the tool's function: submitting a self-computed contract bytecode fingerprint for on-chain attestation. It uses a specific verb (submit/publish) and a specific resource (contract bytecode fingerprint), making the purpose unambiguous and distinct from sibling tools.

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

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

The description explicitly states when to use the tool (after computing a fingerprint) and provides an alternative path for obtaining an agentId via an external HTTP endpoint. It also notes that there is no HTTP-only sibling for this, guiding the agent to the correct external registration route.

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 discloses that the tool is 'Free' and details the returned information (capability, version, cache tier, price paid, on-chain settlement). The verb 'look up' implies a read-only operation, but it does not explicitly state side-effect-freedom or require authentication. Still, it provides useful behavioral context beyond the schema.

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 'Free' and the core purpose. Every sentence contributes value – the first describes what it does, the second specifies when to use it. No wasted words.

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 single-parameter lookup tool with no output schema, the description adequately lists the result fields (capability, version, cache tier, list price, credit, paid price, on-chain settlement). It fully explains the tool's purpose and context. Minor gaps like not-found behavior do not significantly impede understanding.

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

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

The input schema already covers the single parameter 'invocationId' with description 'Invocation id from a receiptUrl.' The tool description does not add further meaning about the parameter beyond referencing 'settled invocation' in the purpose. Baseline 3 is appropriate since schema coverage is 100%.

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 starts with 'Look up what a settled invocation actually charged' – a specific verb and resource. It clearly distinguishes this tool from siblings like tereno_price (for quotes) and tereno_catalog (for catalog data) by focusing on settled receipts/billing verification.

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 explicitly states the intended use: 'Use it to check that a call you or another agent paid for was billed the way it was quoted.' This gives a clear when-to-use signal. It does not explicitly mention when not to use it or name alternatives, but the use case is specific and actionable.

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 burden. It transparently discloses key behaviors: paid per call with x402 pricing, caching and sharing of answers, block-level freshness, and the credit/reuse model. This far exceeds basic read-tool descriptions.

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 reasonably concise. The pricing and sharing details add length but are essential behavioral context, so the trade-off is acceptable.

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 adequately specifies the returned fields (name, symbol, decimals, total supply) and also covers the response freshness and network (Base). The additional economic model context makes the tool's behavior fully understandable.

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

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

The input schema fully describes the single address parameter, including pattern and purpose. The description adds no additional semantics beyond the schema's 100% coverage, so the baseline of 3 is appropriate.

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

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

The description clearly states the tool reads a Base token's name, symbol, decimals, and total supply from a given contract address. It uses a specific verb ('Read') and resource ('Base token'), and this scope distinguishes it from sibling tools like contract_interface.

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 tool is for looking up token metadata but does not explicitly state when to use it versus alternatives. No exclusions or comparisons to sibling tools are provided, so guidance is only 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?

With no annotations, the description carries the full burden, and it does disclose non-obvious behavior: paid per call via x402 on Base at $0.01-$0.05 USDC, a shared-reuse discount, and a bounded credit to the producing wallet. Gaps remain on failure semantics (what happens if execution is not 'clean') and idempotency, but the cost/payment/sharing disclosures go well beyond the schema.

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 opening sentence front-loads the verb, resource, and supported protocols, followed by a detail sentence and a payment sentence. It is dense but every clause carries information; the payment/reuse economics could be tightened slightly but are not 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 one-parameter tool with no output schema and no annotations, the description covers purpose, protocols, pricing, and shared-state seeding well. It does not describe the shape of the notarization result or what is returned when a trade fails the 'clean execution' certification, which is the main remaining 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?

There is a single parameter with 100% schema coverage, and the schema already documents it as a 'Completed transaction hash on Base mainnet.' The description reinforces the 'completed trade' constraint but adds no format, chain, or validation detail 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?

The description states a specific verb (notarize) applied to a specific resource (a completed DEX trade), names the supported venues (Uniswap V4, Aerodrome, Uniswap V3), and enumerates the concrete actions taken (audit receipt, decode deltas/pool state, certify clean execution, seed artifact). The 'completed trade' framing cleanly separates it from the sibling guard tools, which operate before execution.

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 'completed DEX trade' and 'on Base' scoping tells the agent clearly when this tool applies (post-swap notarization), and the pricing sentence implies reuse economics. However, it never names an alternative tool or an explicit when-not condition, so routing against siblings like transaction_intent_guard is left to inference.

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

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

With no annotations, the description carries the full disclosure burden and does well: it states the $0.25 USDC per-call cost via x402 on Base, that the call is private and never cached, shared, or resold, and that the unsigned transaction stays with the paying wallet. Remaining gaps (latency, failure behavior, whether it mutates any state) are minor for a simulation-style 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?

The safety question is front-loaded and the payment/privacy lines earn their place. The second sentence is a long comma-spliced capability list that could be tightened, but overall there is no filler.

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

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

With no output schema and no annotations, the description does useful double duty by naming the classes of results returned (intent, simulation, gas, deltas, scam flags, target/pause state) plus cost and privacy terms. It is complete enough to call correctly, though return shape and latency 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?

All 4 parameters are documented in the schema at 100% coverage, including regex patterns and defaults for data and value. The description adds no param-level meaning beyond that, so the baseline of 3 is appropriate.

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

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

The description states a specific pre-signing safety analysis on Base and enumerates concrete capabilities (intent classification, simulation, gas estimate, balance/allowance deltas, scam/unlimited-approval flags, target change and pause state). It is clearly a transaction-safety guard, but it never distinguishes itself from siblings like contract_guard or aerodrome_swap_guard, so it lands at 4 rather than 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?

'Before signing on Base' gives an implied trigger for use, but the guidance is embedded in a capability list rather than stated as a rule. There is no explicit when-not-to-use and no named alternative among the many sibling guard tools, leaving the agent to infer routing.

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

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

With no annotations, the description carries full behavioral burden and does well: it enumerates what is inspected (bitflags, bytecode, pause status), states the chain (Base), and discloses the payment/sharing model including x402 charging ($0.15–$0.54 USDC) and answer reuse economics. It stops short of describing the verdict/return format, but the cost and analysis-scope disclosure is unusually rich.

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 front-loads the core question and analysis scope before the pricing detail, and every sentence carries distinct information. Minor redundancy from restating the title, and the pricing sentence is dense, but overall it is well-structured.

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

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

For a six-parameter safety-guard tool with no output schema and no annotations, the description covers what is analyzed and the cost model, which is what an agent needs before calling. The gap is that it never hints at the returned verdict structure, which would matter given there is no output schema.

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

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

Schema description coverage is 100%, so the schema already documents all six fields (fee, hooks, currency0/1, poolManager, tickSpacing) with patterns and types. The description mentions 'pool keys' and 'hook' generically but adds no syntax or format 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 names a specific verb set (decode pool keys, inspect hook permission bitflags, verify hook bytecode and pause status) tied to a precise resource (a Uniswap V4 pool and its hook on Base), so an agent knows exactly what analysis it performs. It does not, however, distinguish itself from guard siblings like contract_guard or transaction_intent_guard.

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

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

The framing as a question ('is this safe to interact with?') implies usage as a pre-interaction safety check, which is adequate implied guidance. But there is no explicit when-to-use statement and no mention of the alternative guard tools an agent should weigh against it.

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 of behavioral disclosure. It transparently explains the payment model (x402 on Base, $0.02–$0.03 USDC), reuse mechanics, and optional claim checking. However, it does not describe error behavior (e.g., inaccessible pages), the structure of the output artifact, or how the optional claim check is triggered (no parameter for that). These gaps reduce transparency.

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

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

The description is a single paragraph of about 150 words, with every sentence adding value: main purpose, optional feature, reuse, pricing, and sharing. It is front-loaded with the primary action. While efficient, it could be more scannable with bullet points or shorter sentences, hence not a perfect 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?

The tool has no output schema, so the description must explain return values. It mentions 'bounded, LLM-ready Markdown with a content-addressed artifact' but does not specify the artifact's format, how to re-verify, or what the optional claim check returns. The pricing and reuse details are helpful, but the lack of output clarity leaves the agent with insufficient information to use the tool correctly.

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

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

Schema description coverage is 100%—both 'url' and 'wallet' are already fully described in the input schema. The tool description adds no additional meaning or constraints beyond what the schema provides. According to the rubric, when coverage is high, the baseline is 3, and the description does not exceed that.

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

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

The description clearly states the tool converts a public web page into 'bounded, LLM-ready Markdown' with a content-addressed artifact for verification. It uses specific verbs ('Turn', 'compile') and resource ('public web page'), and distinguishes from siblings by emphasizing the re-verification and payment reuse features, which are unique among the listed sibling tools.

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

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

The description implies when to use the tool (to get a verified, reusable Markdown version of a page) but does not explicitly state when not to use it or compare it to alternatives. It mentions the cost and reuse benefits but lacks direct guidance on distinguishing from similar tools like 'evidence_artifact' or 'tereno_find_claims'.

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