Carredge

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

Annotations cover safety (readOnlyHint, openWorldHint), and the description adds a critical behavioral fact not present in structured data: this is pay-per-call via x402 USDC on Base, and the response contains a payment challenge when payment is absent. That is meaningful operational context an agent must know before invoking.

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

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

Two short sentences, zero filler, with the data scope front-loaded and the payment condition second. 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?

An output schema exists, so return values need not be described, and the payment flow is disclosed. For a no-parameter read tool this is nearly complete; only the relationship to sibling data tools is unaddressed.

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 there is nothing for the description to disambiguate; the baseline for a parameterless schema applies. The description correctly implies a plain fetch with no 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?

Names the specific resource and data categories (fees, mempool, network congestion) for Bitcoin, so an agent knows exactly what it returns. However, it lacks a verb and does not distinguish itself from the sibling 'gas' tool or other market data siblings, which could cause selection ambiguity.

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?

States what data is available but gives no guidance on when to prefer this over alternatives such as 'gas' or 'market_pulse', and no exclusions or preconditions beyond the payment note. Usage context is left entirely to inference.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds important behavioral context beyond annotations: it is pay-per-call via x402 USDC on Base, and a missing payment yields a payment challenge in the response.

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 short and front-loads the calculation types before the payment note. It is efficient, though the first sentence is a cryptic fragment rather than a fully structured statement.

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

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

An output schema exists, so return values need not be explained, and the payment model is disclosed. However, the description does not explain what each edge type computes or when to choose among them, leaving a gap for correct invocation.

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

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

Schema description coverage is 100%, and the single parameter is documented in the schema with the same calculation types. The description repeats that list without adding syntax, defaults, or selection guidance, so the schema carries the 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 names the resource ('Net edge') and lists calculation types, but uses a fragment rather than a clear verb+resource statement. It does not distinguish this tool from siblings such as funding or predictions, leaving the agent to infer that it computes an edge metric for the named strategies.

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

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

No when-to-use guidance or alternatives are provided. The description only lists calculation types and payment details; it never says when an agent should call this tool instead of related siblings.

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?

Beyond the readOnly/openWorld annotations, the description discloses a critical non-obvious behavior: it is pay-per-call via x402 USDC on Base, and the response returns a payment challenge if payment is absent. This is exactly the kind of cost/auth context an agent cannot infer from annotations. It stops short of covering failure modes for non-HTML or paid-response shape.

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

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

Two tight sentences with the core transformation front-loaded and the payment caveat second. Nothing is wasted, though the opening is clipped enough to read as a fragment rather than a full statement.

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

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

With an output schema present, return values need not be described, and the payment flow is explained. For a single-parameter read tool with rich structured metadata, this is close to complete; only handling of non-HTML or failed extraction is unaddressed.

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 there is only one parameter, so the schema already documents the URL. The description reinforces that it must be public and adds nothing about syntax, formatting, or edge cases, so the baseline 3 applies.

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

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

The description states a concrete transformation: a public URL becomes clean Markdown plus metadata, which is far more informative than the bare name/title 'extract'. It is unambiguous about input and output kind, though the phrasing is a noun fragment rather than an explicit verb statement, and there are no sibling tools in the same domain to distinguish against.

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

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

'Any public URL' and the schema's 'must return HTML' imply when this is applicable, but there is no explicit guidance on when to use it versus other options or what inputs are out of scope beyond the HTML hint. Usage is only implied, not spelled out.

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

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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely new operational context: pay-per-call billing, the x402 USDC-on-Base rail, and the fact that the response carries a payment challenge when payment is missing. That last point directly describes a failure mode an agent must handle, which is exactly what annotations cannot convey.

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, zero filler. The data scope is front-loaded and the payment caveat follows immediately; every clause carries information an agent needs.

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

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

With an output schema present, return values and history formatting do not need explaining here. Between the declared data scope and the full payment-flow explanation, there is no gap an agent would need filled before calling this 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?

The tool takes zero parameters and the schema is an empty object, so there is nothing to disambiguate. Baseline for a no-parameter tool is 4, and the description introduces no confusing parameter-like claims.

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 the specific resource (Crypto Fear & Greed Index) and its scope (current + 30d history), which is enough to tell it apart from the broad macro/market_pulse siblings. It does not explicitly contrast with any named sibling, so it stops short of a 5.

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

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

Usage is only implied by the resource name; there is no statement of when to reach for this versus market_pulse, btc_stats, or macro. It does surface one real precondition — that calls are pay-per-call — which is more than pure silence, but no alternatives 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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful non-obvious behavior: it is pay-per-call via x402 USDC on Base, and a payment challenge is returned when payment is missing, which an agent must know before calling.

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

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

Two compact sentences that front-load what the tool returns and then the payment model. No filler, though the fragment style ('+ extremes') is terse to the point of slight ambiguity.

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

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

With an output schema present, return values need no explanation, and a parameterless tool needs no param docs. The description covers scope and payment model, but omits how the tool relates to the similar funding_history sibling, 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?

The tool takes zero parameters, so the baseline of 4 applies. There is nothing for the description to clarify beyond what the empty schema already conveys.

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 resource and scope: perp funding rates aggregated across 5 exchanges plus extremes. It is clearly a data-retrieval endpoint, but it never distinguishes itself from the sibling funding_history, which an agent could easily confuse it with.

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

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

There is no when-to-use guidance, no mention of the sibling funding_history, and no conditions under which this tool should be preferred over it. Usage is only implied by the tool name and the pay-per-call note.

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?

Beyond the readOnlyHint/openWorldHint annotations, the description discloses a genuinely important behavioral trait: this is a pay-per-call tool billed in x402 USDC on Base, and the response returns a payment challenge when payment is absent. That is exactly the kind of cost/auth behavior an agent must know before calling. It stops short of describing pagination or rate limits, so not a 5.

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

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

Two tight sentences with zero filler. The capability statement is front-loaded and the payment caveat follows immediately, so the most decision-relevant facts land first.

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

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

With a full output schema present, return values need no explanation, and the schema covers all parameters. The one omission is sibling differentiation from 'funding', but the payment-flow disclosure makes this definition complete enough to invoke 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% and all three parameters (days, symbol, exchange) are documented with defaults and ranges in the schema itself. The description adds only the 'up to 90 days' ceiling, which duplicates the schema's '1-90' range, so the baseline 3 applies.

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

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

The description states a specific resource and scope: multi-exchange funding rate history up to 90 days. It is clear what the tool returns, but it never distinguishes itself from the sibling 'funding' tool, which an agent would reasonably consider an alternative for funding-rate data.

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

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

There is no when-to-use, when-not-to-use, or alternative-tool guidance. The closest thing to routing information is the 90-day scope, which merely restates a parameter constraint rather than telling the agent when this tool is the right pick over 'funding'.

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

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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely new behavioral context: this is pay-per-call via x402 USDC on Base, and a missing payment yields a payment challenge in the response rather than a normal result. That failure-mode disclosure is valuable. It omits pricing amount and any rate limits, keeping it short of a 5.

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

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

Two dense sentences, zero waste: the data scope is front-loaded and the payment caveat follows immediately. Every clause (source, latest + 30-day history, payment mechanism, challenge-on-missing-payment) carries information an agent needs.

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

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

With an output schema present, return-value detail is not required, and the description still summarizes the payload (latest + 30-day history). Payment mechanics and the failure path are covered, which is the main risk for this tool. Missing only edge-case behavior such as unsupported currency codes or rate limits.

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 both parameters ('from'/'to' ISO codes with defaults) are already fully documented in the schema, so the baseline is 3. The description adds only the notion of 'any pair' and the ECB source, not per-parameter semantics such as accepted code formats or behavior when a pair is unsupported.

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 resource and scope: 'FX rates for any pair (ECB): latest + 30-day history.' An agent immediately knows this returns currency exchange rates plus history, which is clearly distinct from the crypto/macro siblings. It stops short of naming any sibling or boundary, so it is clear but not differentiating-by-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?

Usage is only implied by the domain statement — an agent infers 'call this for FX conversion/rates,' and the ECB source hints at official reference rates rather than market quotes. There is no explicit when-to-use, when-not-to-use, or alternative (e.g. yields for interest rates), so guidance is implicit 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?

Annotations declare readOnlyHint and openWorldHint, so the safety profile is already covered. The description adds meaningful context beyond that: the x402 USDC pay-per-call model on Base and the fact that the response includes a payment challenge when payment is missing — critical operational behavior an agent must know.

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 no waste — the data scope is front-loaded and the payment mechanic follows. Every sentence earns its place.

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

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

For a no-parameter tool with an output schema, the description covers data scope, unit, payment requirement, and the missing-payment response behavior. Nothing an agent needs to invoke it correctly is absent.

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

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

With zero parameters, the 4 baseline applies; there is nothing for the description to disambiguate. The chain list and gwei unit are useful contextual framing but do not substitute for parameter documentation.

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 resource (multi-chain gas prices), the exact chains covered, and the unit (gwei), which no sibling tool provides. An agent can identify this as the gas-price tool immediately without opening the schema.

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

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

Usage is implied by the name and by the absence of any sibling covering gas prices, but the description never states when to call this versus alternatives or under what conditions. No explicit when/when-not guidance is present, though the payment note partially compensates.

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

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

Annotations only declare readOnlyHint and openWorldHint; the description goes further by disclosing the cost model (x402 USDC on Base, pay-per-call) and the failure-path behavior that the response returns a payment challenge when payment is missing. That is meaningful context an agent cannot infer from structured fields.

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, front-loaded with the resource and scope before the payment caveat. Every clause carries information; the parenthetical '(official)' is the only slightly soft element.

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

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

With an output schema present, return values need no explanation, and the description covers the critical non-obvious behavior (payment challenge). For a zero-required-param lookup tool this is nearly complete, though it says nothing about unsupported countries or failure modes 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 100% with both parameters documented (year format/default, country ISO code), so the schema carries the burden. The description adds nothing parameter-specific beyond the country/year scope already implied.

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 resource (public holidays) with scope qualifiers (any country/year, official). It is unambiguous and clearly distinct from every sibling, which are all finance/crypto/market tools, but it lacks an explicit verb framing (list/retrieve).

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, nor prerequisites such as needing a funded wallet. The only contextual cue is the payment model, which is behavioral rather than usage guidance.

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

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

Annotations already declare readOnlyHint and openWorldHint. The description adds critical behavioral context: it is pay-per-call via x402 USDC on Base, and the response includes a payment challenge if payment is missing. This goes beyond annotations but does not cover data freshness or idempotency.

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 tightly written sentences with no waste. The first sentence front-loads the data content, and the second addresses the payment requirement and failure mode.

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 zero parameters, a rich output schema, and annotations covering read-only/open-world behavior, the description provides all necessary context: what data is returned and the payment mechanism. Nothing material is missing for an agent to invoke it correctly.

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

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

The tool takes zero parameters, so there is nothing to document. The description appropriately does not waste space on parameter semantics; baseline for zero params is 4.

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 resource (US macro data) and enumerates the key indicators (CPI, unemployment, payrolls, earnings), making it distinguishable from most siblings. However, it does not explicitly contrast itself with overlapping tools like yields or treasury.

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 alternatives. It only describes what data is returned and the payment model, leaving the agent to infer usage context.

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

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

Annotations cover read-only and open-world safety, but the description adds critical non-annotation behavior: it is pay-per-call via x402 USDC on Base, and a missing payment returns a payment challenge. This is exactly the kind of operational detail an agent needs and is not in the annotations or schema. It doesn't cover rate limits or error modes beyond payment, so not a 5.

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

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

Two tightly written sentences front-load the aggregation scope and then the payment model. Every phrase earns its place; no redundant restatement of the name or 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?

With an output schema present, the description does not need to detail return fields; it focuses on the aggregation promise and the payment requirement. Annotations already carry safety, and the schema documents the symbol parameter fully, so the definition is sufficient for correct invocation.

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

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

Schema description coverage is 100% for the single optional symbol parameter, including the BTC default. The description adds no additional syntax, format or semantic 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 names the resource (market pulse) and enumerates the exact metrics returned—price, 24h change, volume, cross-venue funding and OI—so the agent knows what it does. It differentiates from single-metric siblings like funding and open_interest by emphasizing 'One call' aggregation, though it doesn't name those siblings explicitly.

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

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

The phrase 'One call' implies the tool is an aggregate alternative to calling separate tools, but the description never states explicit conditions for using it versus siblings like btc_stats, funding or open_interest. No when-not or prerequisite guidance is given, leaving usage 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?

The annotations already cover the safety profile (readOnly, openWorld), and the description goes meaningfully beyond them by disclosing the x402 USDC-on-Base payment model and, crucially, that a missing payment produces a payment challenge in the response rather than an error. It does not mention freshness, caching, or rate behavior, keeping it short of a 5.

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

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

Two sentences, zero filler, with the primary capability front-loaded ahead of the payment caveat. Nothing could be removed without losing real 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 single-parameter, output-schema-backed tool with readOnly/openWorld annotations, this covers what an agent needs: the return content, the format, and the non-obvious payment/failure behavior. Only minor operational details (data freshness, update cadence) are absent.

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

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

Schema description coverage is 100% — the single 'limit' parameter and its default of 15 are fully documented in the schema, and the description adds nothing about it. Baseline 3 applies when the schema carries the parameter meaning.

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

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

The description states exactly what the tool returns — the latest crypto news headlines — and adds the delivery format ('clean JSON'). No sibling tool (btc_stats, market_pulse, macro, etc.) covers news, so there is no ambiguity to resolve.

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 resource name rather than stated: there is no explicit 'use this when...' guidance, though the absence of a competing news sibling makes the choice obvious. The pay-per-call note gives some operational context for deciding whether to invoke 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?

Annotations cover read-only and open-world hints, and the description adds genuinely useful behavioral detail beyond them: the pay-per-call x402/USDC-on-Base model and the fact that a missing payment yields a payment challenge in the response. It stops short of noting rate limits or failure modes beyond payment.

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, front-loaded with the data content before the payment caveat. No wasted clauses, though the payment sentence is dense with jargon that could be split for 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?

An output schema exists, so return-value explanation is unnecessary, and the description covers data content plus the payment prerequisite. Given the trivial one-parameter schema, an agent has nearly everything needed to call it correctly.

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

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

Only one parameter with 100% schema coverage, so the schema already documents the symbol format and default. The description adds nothing about symbol syntax or behavior when omitted, making 3 the correct 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?

States a specific resource (perp open interest) with named data sources (Binance+Bybit) and enumerates the three data views returned: current, 24h change, hourly series. It is clearly distinguishable from siblings like funding or options, though it does not name a sibling explicitly.

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

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

There is no guidance on when to reach for this tool versus funding, funding_history, or market_pulse. The only context offered is the payment mechanism, which is a constraint rather than usage direction.

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

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

Annotations already flag readOnlyHint=true and openWorldHint=true, so the bar is lower, yet the description adds real operational context: it is pay-per-call via x402 USDC on Base, and the response carries the payment challenge when payment is missing. That payment/auth behavior is exactly the kind of trait annotations do not convey.

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

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

Two compact clauses, front-loaded with the data delivered and followed by the payment model. No filler 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?

With an output schema present, return values need no explanation, and the description covers both content and payment behavior for a one-parameter tool. Only the currency parameter's role is left entirely to the schema, 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 coverage is 100% for the single currency parameter, so the schema already documents the BTC/ETH default. The description adds no additional meaning about the parameter, which matches the baseline 3.

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

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

The description names a specific verb/resource: a Deribit volatility surface returning IV per expiry plus ATM greeks. That is concrete enough to separate it from siblings like funding, open_interest or btc_stats, though it never explicitly says so.

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 alternatives such as funding or open_interest, and no conditions or prerequisites are given. The payment note describes mechanics, not usage guidance.

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

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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely new operational context by disclosing the pay-per-call model (x402 USDC on Base) and the error-path behavior — a payment challenge is returned in the response when payment is missing. It stops short of naming the price, rate limits, or refresh cadence, so not a full 5.

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

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

Two sentences, no filler: the data scope comes first, the payment/cost constraint second. Every clause earns its place and nothing is repeated from the name or schema.

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

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

An output schema exists, so return-field documentation is unnecessary, and the description covers the non-obvious billing path. The main residual gap is scope — it never says which venues are aggregated or how fresh the quotes are, which matters for a multi-venue price feed.

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 limit and minVolume are already fully documented in the schema, and the description adds no filtering syntax, venue scoping, or default rationale beyond it. Baseline 3 applies when the schema carries parameter meaning.

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

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

Names the resource precisely — prediction market prices plus YES+NO deviations — so an agent knows exactly what data comes back, and it is clearly distinct from the other data-feed siblings (funding, tvl, yields). It lacks an explicit verb and does not contrast itself with any sibling, but the domain is unambiguous.

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

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

The description states no when-to-use condition, no prerequisites, and no alternatives. Nothing tells an agent when this feed is the right choice over market_pulse, edge, or options, nor whether the call should be avoided when budget or payment is unavailable.

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

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

Annotations cover the read-only and open-world profile, and the description adds genuinely useful non-annotation behavior: it is pay-per-call via x402 USDC on Base, and a missing payment yields a payment challenge in the response. It does not mention rate limits or latency, but the payment mechanic is the key operational disclosure.

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

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

Two tight sentences: the capability and its outputs come first, the payment caveat second. Zero filler and no 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?

An output schema exists so return values need not be explained, yet the description still previews the verdict field. Combined with the payment behavior disclosure, an agent has everything needed to call it correctly.

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

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

Only one parameter (repo), and schema coverage is 100% with a format hint and example ('owner/name, e.g. facebook/react'). The description adds nothing 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?

Names the specific resource (GitHub repo health) and enumerates what it returns — stars, issues, releases, and an ACTIVE/STALE/ARCHIVED verdict — which is a precise, non-tautological statement of function. No sibling tool covers repositories, so differentiation is unnecessary.

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

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

Usage is only implied: an agent can infer 'call this to assess a GitHub repo,' but there is no statement of when to prefer it, prerequisites, or exclusions. No sibling offers an alternative path, so the gap is modest but real.

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

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

Annotations already cover read-only and open-world semantics, and the description adds genuinely new operational context: it is pay-per-call via x402 USDC on Base, and a missing payment returns a challenge in the response. That payment/auth behavior is not derivable from the annotations or schema, which is exactly the value expected here.

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 zero filler: the data scope comes first, then the payment constraint. Every clause carries information an agent needs.

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

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

With an output schema present, return-value detail is unnecessary, and the description covers the unusual bits an agent must know (payment requirement). It is largely complete, though it omits things like historical range, reporting period coverage, or rate limits.

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 description coverage ('US company ticker symbol, e.g. AAPL or MSFT'), so the schema fully documents it. The description adds no format, exchange, or format-variant detail beyond that, 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?

States a specific resource and data domain: US company financials from XBRL, with concrete fields (revenue, net income, EPS). That clearly separates it from the crypto/macro-dominated sibling set, though it doesn't explicitly name a sibling to differentiate against, so it falls short of 5.

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

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

The description says what data it returns but never states when to reach for it versus alternatives, nor any exclusions or prerequisites beyond the payment note. An agent gets no routing guidance other than the implicit ticker-based scope.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the pay-per-call x402 USDC on Base payment model and the fact that a payment challenge is returned when payment is missing, which an agent must know to handle the response correctly.

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 what the tool returns and followed by the payment caveat. Every clause earns its place; nothing is padded or repeated.

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

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

An output schema exists, so return values need no explanation, and the payment behavior is disclosed. The one gap is that the history-window parameter is never acknowledged in prose, but the schema covers it, leaving the definition largely complete for a simple read 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% and the single 'months' parameter is fully documented in the schema with its default, so the schema carries the semantics. The description adds no parameter detail, 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 names the specific resource (US Treasury rates) and the scope of coverage (bills, notes, bonds, TIPS), which is enough for an agent to distinguish it from generic siblings like yields or macro. It does not explicitly contrast itself with the closest sibling, yields, but the 'official US Treasury by security type' framing is specific and non-tautological.

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 rather than stated: an agent can infer this is the tool for official Treasury curve data, and the description notes the security types available. However, it gives no explicit when-to-use versus alternatives (e.g. yields), no conditions, and no exclusions.

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

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

Annotations already cover read-only and open-world traits, and the description adds real operational context beyond them: it is a pay-per-call endpoint billed in x402 USDC on Base, and a missing payment returns a payment challenge rather than an error. That payment/auth behavior is exactly the kind of disclosure annotations cannot provide.

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 tightly packed sentences with zero filler: data scope first, payment behavior second. Everything is front-loaded and no sentence 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 an output schema present, return values need no explanation, and the payment flow is disclosed. The only minor omission is what happens on filtering by an unknown chain, but for a simple one-param read tool this is effectively 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 coverage is 100% and the single optional chain parameter is fully documented in the schema with an example (Ethereum). The description's only added semantic is the top-15 default when chain is omitted, which the schema already hints at, so this sits at 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?

States a specific resource (DeFi TVL), the data source (DeFiLlama), the scope (by chain, top 15 + total), so an agent knows exactly what the tool returns. It is clearly distinct from siblings like yields, funding, or macro.

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

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

Usage is only implied: the optional chain param and the note that omission yields the top-15 ranking convey the default behavior, but there is no explicit when-to-use guidance or comparison to sibling tools such as yields for protocol-level data.

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

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuinely non-obvious behavior: this is a pay-per-call endpoint billed in x402 USDC on Base, and a missing payment yields a payment challenge in the response rather than an error. That discloses a multi-step protocol an agent could not infer from 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 compact sentences with zero filler. The core capability is front-loaded and the payment caveat follows, which is the right ordering for an agent scanning for fit.

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

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

With an output schema present, return values need no explanation, and the unusual payment model is called out. The only remaining gap is the mechanics of satisfying the payment challenge (whether it is automatic or requires a separate call), which the agent must infer.

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 single 'q' parameter is already documented with examples ('London or Madrid'). The description adds no syntax, format, or constraint beyond what the schema supplies, 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 names a specific resource and scope: weather for any city, with current conditions plus a 3-day forecast. This is immediately distinguishable from the sibling tools (fx, gas, yields, etc.), none of which cover weather. No ambiguity about what the tool returns.

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 description ('weather for any city'), and there is no competing sibling to route against, so no explicit when/when-not is needed. However, it never states prerequisites such as needing a funded wallet before the first call, leaving the caller to discover the payment flow by failure.

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

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

Annotations already declare a safe read against an open world, and the description adds genuinely non-obvious behavior: this is a pay-per-call endpoint billed in x402 USDC on Base, and a missing payment returns a payment challenge rather than data. That failure-mode disclosure is valuable. It does not cover freshness/caching or rate limits, so it falls short of a 5.

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

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

Two sentences, zero waste: the resource and source come first, the payment mechanics second. 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?

An output schema exists, so return values need no explanation, and the description covers purpose plus the billing/failure behavior an agent must handle. It leaves the 'stablecoin-only' scoping and any freshness guarantees unstated, which is a minor gap for a simple optional-param listing 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%, so the schema already documents chain, limit, and minTvl with formats and defaults. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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

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

States a specific resource (DeFi stablecoin pool APYs) and its data source (DeFiLlama), which is enough to distinguish it from the TVL, funding, and edge siblings that cover other DeFi metrics. It does not explicitly name those siblings, so differentiation requires the agent to infer from the resource noun.

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 resource ('get pool yields'), and the payment precondition is stated, but there is no guidance on when to prefer this over tvl or funding, nor any exclusions. The agent must infer the use case.

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