Crypto MCP

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

With no annotations, the description carries the full burden. It usefully discloses the default-latest behavior and the network-specific quirk that 'numero' is ignored on Solana, but says nothing about read-only nature, error behavior, or what the returned block data contains.

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

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

Very compact and front-loaded, with the key behavior ('último' default) stated in the first line before the argument details. No wasted sentences, though the 'Args:' block is slightly terse.

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 2-parameter read tool with no output schema and no annotations, the description covers the parameters and the default behavior adequately. It leaves gaps around return value contents and error cases, which an agent would need when interpreting results.

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

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

Schema description coverage is 0%, so the description must compensate, and it does: it enumerates the valid 'red' values (base, ethereum, solana) and explains 'numero' as a block number that only applies to EVM chains. This adds real meaning the bare schema lacks, though it doesn't clarify the default empty-string semantics of 'numero'.

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 (block data) with a clear default behavior when the block number is omitted. It is distinguishable from siblings like transaccion or estado by resource, but never names or contrasts with any sibling explicitly, so it stops short of a 5.

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

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

The phrase 'sin número, el último' tells the agent what happens when 'numero' is omitted, which is useful usage context. However, there is no guidance on when to prefer this tool over siblings such as transaccion or estado, so usage 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 one real behavior: the fields are returned only 'si los expone', warning that results may be empty or partial. It says nothing about read-only nature, failure modes for invalid addresses, or supported chains beyond the two named. Useful but thin disclosure for an annotation-free tool.

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

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

One front-loaded sentence stating the return payload, followed by a compact Args block. No filler, no restatement of the tool name, and every line 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?

There is no output schema and no annotations, so the description must cover everything; it states the returned fields and their conditional presence but omits error behavior for non-contract addresses and how to proceed when fields are absent. Adequate minimum for a 2-param read tool, but with visible gaps.

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

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

Schema coverage is 0% — the schema offers only bare titles 'Red' and 'Contrato'. The description compensates by enumerating the accepted values for red (`base` o `ethereum`, effectively an enum absent from the schema) and clarifying that contrato is a contract address. That is meaningful added meaning, held back from 5 only because formats are still not fully pinned down.

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 the resource (contrato) and exactly what it returns: símbolo, nombre y decimales. That is more specific than the sibling names like estado or precio, and an agent can tell this is the metadata lookup rather than a balance or price call. It lacks an explicit verb and never names a sibling it differs from, 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?

There is no when-to-use guidance beyond the implied 'fetch contract metadata'. It never says how this relates to es_contrato (checking whether an address is a contract) or when the two should be chained. The qualifier 'si los expone' hints at a precondition but is not framed as usage advice.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a read-only verification but never states that it is non-mutating, what permissions are required, or what the result looks like (boolean vs address), leaving meaningful gaps.

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

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

The description is short, front-loaded with the core purpose, and the Args block is compact. Every element serves a purpose, though the purpose sentence could be tightened.

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

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

For a simple two-parameter read check with no output schema, the definition is mostly adequate, but it omits the return shape and any note on network-specific behavior. A brief statement of what is returned would close the 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?

Schema description coverage is 0% with no enums, so the description must compensate and largely does: it enumerates valid `red` values (base, ethereum, solana) and clarifies that `direccion` is the address to check. It adds real meaning the bare schema lacks.

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 purpose: distinguishing a contract from a normal wallet (EOA), which is a clear verb+resource outcome an agent can understand. It does not explicitly differentiate itself from siblings like contrato_info, but the core purpose 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?

There is no guidance on when to use this check versus alternatives such as contrato_info, nor any exclusions or prerequisites. The agent must infer usage context entirely.

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

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

No annotations are provided, so the description carries the full disclosure burden. It does reveal the return content (service status plus available networks), which implies a safe read operation, but says nothing about authentication needs, rate limits, or freshness of the status data.

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

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

A single short sentence that front-loads the resource and the returned information. There is 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?

The tool is a zero-parameter, low-complexity status query with no output schema, and the description covers both its purpose and the general shape of what it returns. For a tool of this simplicity, that is close to sufficient, though a hint of the status fields would make it 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 tool takes zero parameters, so per the baseline there is no parameter semantics to document and no risk of ambiguity. Nothing in the description is needed to compensate.

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

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

States a specific verb ('Devuelve') and resource ('el estado del servicio y las redes disponibles'), so the agent knows exactly what it retrieves. It does not explicitly distinguish itself from siblings like bloque or saldo, but its scope is distinct enough to be identifiable.

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

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

There is no guidance on when to call this versus the sibling tools (bloque, contrato_info, saldo, transaccion, etc.). Any usage context must be inferred from the name and description alone.

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

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

No annotations are provided, so the description must carry the behavioral burden. It discloses that the tool returns the current gas price in gwei, implying a read-only query, but does not explicitly state read-only behavior, permissions, rate limits, or error behavior.

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

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

Extremely concise and front-loaded: the core purpose and unit come first, followed by the only parameter's accepted values. No wasted text.

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

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

For a simple one-parameter read tool with no output schema, the description is largely complete: it states the returned value and unit and documents the parameter values. It lacks explicit usage guidance and read-only/behavioral assurances, but the complexity is low.

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

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

Schema description coverage is 0% and the single parameter has no schema-level description. The description compensates well by naming the parameter and listing its allowed values: `base` or `ethereum`, though it does not explicitly say these represent networks.

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 clear and specific resource: current gas price in gwei. It implicitly distinguishes current gas price from historical price via 'actual', but does not explicitly name sibling alternatives such as historico_precio or precio.

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

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

Provides no explicit guidance on when to use this tool versus alternatives. The word 'actual' implies current rather than historical pricing, but no when-to-use or when-not-to-use conditions are 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?

No annotations are provided, so the description carries the full load. It usefully discloses what the result contains (minimum, maximum, variation), which serves as lightweight output disclosure, but says nothing about data availability, symbol restrictions, or error behavior for unsupported values.

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

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

The core purpose is front-loaded in one sentence, followed by a compact Args block. The parameter lines each add real information rather than restating the schema titles.

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 appropriately names the returned metrics, and it documents all three inputs with allowed values. For a simple read-only market lookup the remaining gaps (required flag, unsupported-input behavior) are minor.

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

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

Schema description coverage is 0%, so the description must compensate, and it largely does: it names all three parameters and supplies value sets the schema lacks (dias as 1/7/30/90, moneda as usd/eur/pen) plus a symbol format example ('btc'). It stops short of stating which are required or the default behavior.

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: price evolution over recent days with min, max and variation. It is clearly distinguishable from the sibling 'precio' by its historical window, though the description never explicitly contrasts the two.

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: asking for the last N days naturally means historical trend analysis rather than a spot quote. There is no explicit 'use this instead of precio when...' statement and no mention of prerequisites or limitations.

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

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

No annotations are provided, so the description carries the full behavioral burden. It hints at a read-only lookup ('consultar') but discloses nothing about return format, whether the value counts pending vs confirmed separately, or any constraints — for a no-annotation tool this is a significant gap.

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?

Short and front-loaded with the concept, followed by a compact two-argument block. The concept sentence answers 'what is a nonce' rather than 'what does this tool do', but nothing is padded.

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 leaves the return value ambiguous — it does not say whether a number, a list, or both confirmed and pending counts are returned. For a simple 2-param query tool this is adequate but not 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 0%, so the description must compensate and it largely does: it gives the allowed `red` values (`base` or `ethereum`), which the schema lacks as an enum, and explains `direccion` as the wallet whose counter is queried. This is real added value over the bare schema.

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

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

The description defines what a nonce is (sent transactions, confirmed and pending) but never states the tool's action as a verb — it never says it returns the counter for an address. The arg note ('Cartera cuyo contador se quiere consultar') implies the query, but the purpose is inferred rather than declared, and it does not distinguish itself from siblings like transaccion or saldo.

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

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

There is no explicit when-to-use or when-not-to-use guidance and no named alternative among siblings such as transaccion or estado. Usage is only weakly implied by the argument notes.

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

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

No annotations are provided, so the description carries the full disclosure burden. It implies a read-only price lookup but never states side effects, authentication needs, rate limits, or whether a missing symbol is an error. This is a significant gap for a tool with zero annotation coverage.

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?

Purpose is front-loaded in one sentence, followed by a compact Args block. Every line earns its place; there is no filler, though the formatting is slightly verbose for two parameters.

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 2-parameter read tool the description covers purpose and both parameters adequately. With no output schema, however, it says nothing about what a quote returns (price field, base/quote pairing), leaving a real gap an agent would want closed.

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 0% schema coverage the description must compensate, and it largely does: it documents both parameters' comma-separated string format and gives concrete examples (btc,eth,sol / usd,eur,pen). It omits the fact that monedas defaults to usd, which the schema carries but never explains.

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 opening sentence states a specific verb+resource: fetching the market quote (cotización de mercado) for one or more symbols. It is clearly distinguishable from blockchain siblings like saldo, transaccion, estado, though it never explicitly names or contrasts them.

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

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

There is no indication of when to use this tool versus alternatives, no prerequisites, and no exclusions. Usage is only implied by the tool name and resource ('market quote').

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

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

No annotations are provided, so the description carries the full burden. It implies a read-only balance lookup, but does not disclose whether it hits the chain live, what happens on an invalid/unknown address, or latency/rate-limit behavior. It does at least enumerate the valid network values, adding real behavioral context.

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

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

Front-loaded with the core purpose in the first sentence, followed by compact args documentation. Little waste, though the leading label repeats the tool name and the Args block is somewhat duplicative of the 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?

No output schema and no annotations exist, so the description could say more about the return value (balance units, formatting) and error behavior. For a simple two-parameter read tool it is adequate but leaves those gaps open.

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

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

Schema coverage is 0% and the schema has no enums, so the description must compensate. It does: it lists the three allowed 'red' values (base, ethereum, solana) that the schema omits, and defines 'direccion' as the account address on that network.

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

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

States a specific verb+resource: retrieves the native balance of an account, and clarifies which asset per chain (ETH on Base/Ethereum, SOL on Solana). The word 'nativo' implicitly separates it from saldo_token, though it never names that 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?

Usage is only implied via the 'nativo' qualifier, which is the key distinction from the sibling saldo_token. It never states when to use this vs saldo_token, nor any prerequisites (e.g., valid address format).

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

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

With no annotations the description carries the full burden. It does disclose one behavioral trait beyond the schema: the returned balance is scaled with the decimals read from the contract itself, and 'direccion' is framed as a read of a position. It omits error behavior for invalid addresses, supported-network limits, and any output shape detail.

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 plus a compact Args block, front-loaded with what the tool returns, followed by per-parameter meaning. 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 three-parameter read-only query with no output schema and no annotations, the description covers what is returned (balance with contract decimals) and each input. Only minor gaps remain around unsupported networks and failure modes.

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

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

Schema description coverage is 0% and no enum is declared, so the description does real work: it gives the allowed values for 'red' ('base' or 'ethereum') and clarifies that 'token' is a contract address and 'direccion' is the wallet being queried. Address-format or checksum expectations are still unstated.

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

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

States a specific verb+resource: the balance ('saldo') of an ERC-20 token, qualified as ERC-20 to distinguish it from a generic native-balance tool. However, it never names the sibling 'saldo' explicitly, so the agent must infer the split between native and token balances.

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

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

Provides no when-to-use or when-not-to-use guidance and never references the sibling 'saldo'. The agent is left to infer that this tool is for ERC-20 positions and that 'saldo' covers the native case.

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

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

No annotations are provided, so the description carries the full behavioral burden, and it does disclose the returned facets (status, block, value, commission), which implies a read-only lookup. However it says nothing about error behavior for an unknown signature, whether an unconfirmed/pending transaction is acceptable, or any rate or permission constraints. Partial coverage of the behavioral profile warrants a 3.

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 text is short, front-loaded with the outcome, and uses a clean Args block. Every line earns its place, though the repeated 'red'/'firma' labels add slight boilerplate without further explanation.

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

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

For a simple two-required-parameter tool with no output schema and no annotations, the description covers the lookup semantics and parameter meanings adequately. It is still thin on failure modes, pending-transaction handling, and any constraints the caller must respect before invoking it.

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

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

Schema description coverage is 0%, so the description must compensate, and it does add real meaning: red is enumerated as base/ethereum/solana, and firma is clarified as an EVM transaction hash vs a Solana signature. It still omits format details (hex length, casing, whether base is on Base mainnet) and does not mark them as required.

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 (una transacción) and enumerates exactly what it returns: estado, bloque, valor y comisión. That is more specific than a bare noun label and an agent can tell it apart from siblings like saldo or precio by the returned fields. It lacks an explicit verb and does not differentiate itself from estado or bloque, which overlap thematically, 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?

There is no when-to-use guidance, no conditions, and no mention of alternatives such as bloque or estado, which are the most likely competing siblings. The reader must infer that this tool is for inspecting a single transaction given its network and hash/signature.

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