agentforge

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

With no annotations provided, the description carries the burden. It discloses that this is a scan operation, lists specific risk detectors (unlimited ERC-20 approvals, unverified spenders, Soana delegate authorities), and says it returns a risk assessment. This is transparent about the read-only, non-destructive nature and the output at a high level.

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

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

Three focused sentences with no wasted words. The main purpose is front-loaded, the chain details are organized clearly, and every sentence contributes to a practical understanding of when and how to invoke the tool.

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

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

For a two-parameter tool with no output schema, the description provides the essential context: input address format, supported chains, what will be detected, and the return type. The only notable gap is that the 'risk assessment' output structure is not described, which would help an agent interpret the result, but it is not blocking 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 covers 100% of parameters with descriptions, and the description adds useful chain-specific meaning: EVM address format versus Soana base58, and what the chain parameter controls. It adds value beyond the schema rather than merely repeating it.

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

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

The description starts with a clear verb-object statement, 'Scan a wallet for risky token approvals,' and then specifies exactly what it detects on EVM versus Solana. It differentiaes itself from Solana-only siblings by covering both chain families and zeroes in on a distinct risk category.

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

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

The description explains the intended use case: scanning a wallet for token approval risks, with clear chain-specific guidance. It doesn't explicitly list alternatives or when-not-to-use cases, but the context is clear enough for an agent to decide when this tool is appropriate.

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

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

With no annotations, the description carries the full behavioral disclosure burden. It usefully describes output categories: vulnerabilities, gas optimizations, and best-practice flags. However, it does not disclose whether the analysis is static/heuristic, whether it returns line-level detail, or what limitations apply.

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

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

Three short, front-loaded sentences with no filler. Each sentence covers a distinct aspect: domain/outcomes, capability categories, and supported languages, making the description dense and easy to scan.

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

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

The tool has moderate complexity, no output schema, and no annotations, so the description needs to carry more weight. It covers purpose and capability but omits usage guidance and expected response shape, leaving some agent expectations underspecified.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds light meaning by mapping focus areas to concrete outcomes and echoing the supported language enum, but it does not add meaning beyond the schema for 'code' or 'previousCode'.

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 resource ('smart contract') with specific verbs: 'Finds vulnerabilities, suggests gas optimizations, flags best practice violations.' It clearly differentiates this code-analysis tool from transaction, token, and monitoring siblings.

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

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

The domain ('Smart contract security analysis') and supported languages loosely imply when to use the tool, but there are no explicit conditions, exclusions, or named alternatives. An agent must infer which sibling tools this should be preferred over.

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 only mentions output content and the 'verified' constraint; it does not state whether the operation is read-only, how it handles unverified or invalid addresses, or any other behavioral traits such as failure modes.

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

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

The description is two concise sentences with the primary action front-loaded and no filler. The return-value list is informative without redundancy.

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

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

The core invocation is clear: address is required, chain defaults to ethereum, and output categories are named. But with no output schema and no annotations, the description does not fully cover return-value shape, failure behavior, or routing against sibling tools. It is adequate but leaves meaningful 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 description coverage is 100%, so the schema already documents all parameters — address, chain enum, and focusFunctions. The description adds no parameter-level meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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

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

The description uses a specific action ('Generate documentation') and names the target resource ('any verified EVM smart contract'), plus it lists concrete outputs like risk flags and security posture. It is clear about what the tool produces, though it does not explicitly differentiate itself from sibling tools such as code_review or contract_monitor.

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 'any verified EVM smart contract' implies the tool is for generating contract documentation, giving a broad use case. However, it provides no guidance on when to prefer this tool over siblings like code_review or contract_monitor, and no exclusions or prerequisites beyond 'verified'.

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

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

With no annotations provided, the description carries the full behavioral disclosure burden. It discloses that the tool monitors recent activity for specific categories, which is useful, but it does not explicitly state that it is read-only, what the returned alert format looks like, how 'suspicious' is determined, or whether it queries on-chain or relies on off-chain indexes.

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

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

The description is a single, information-dense sentence that front-loads the verb and resource, then lists the specific event types monitored. Every word adds value and there is no redundant or filler content.

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 3-parameter read-oriented tool, the description and schema cover invocation adequately. However, since there is no output schema, the description should have provided some indication of what the tool returns (e.g., a list of flagged events or risk summaries), and it does not.

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

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

Schema description coverage is 100%, so the schema already documents chain, address, and lookbackHours clearly. The description adds no extra parameter semantics beyond aligning 'recent' with lookbackHours, so the baseline score of 3 is appropriate.

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

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

The description states a specific verb ('Monitor') and resource ('recent contract activity'), enumerating concrete signal types: suspicious admin operations, proxy upgrades, ownership changes, and pause events. It is clear and not a tautology, though it does not explicitly contrast itself with any sibling tool like approval_scan or code_review.

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

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

The description implies the tool should be used when the agent needs to detect risky governance or admin activity on a contract, which provides some usage context. However, it offers no explicit when-to-use versus alternatives, no exclusion cases, and no mention of when another tool like code_review or token_intel would be more appropriate.

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 discloses the core behavior (current gas prices by speed category and trend analysis), but it does not mention return units, data source, freshness, or how trend analysis is derived. This is adequate for basic selection but leaves invocation expectations incomplete.

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

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

One sentence conveys the tool's purpose and the main information returned with no filler. The core output (slow/standard/fast prices) is front-loaded, and the trend-analysis add-on is brief but relevant.

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

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

For a one-optional-parameter read tool, the description is nearly complete: it names the output categories and mentions trend analysis. However, with no output schema, a bit more detail on the trend output format or price units would make it fully self-sufficient.

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

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

The single parameter is fully described in the schema as 'Blockchain network' with an enum of supported chains. The description adds no parameter-specific meaning beyond 'supported EVM chain,' so it does not improve on the 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 clearly states a specific action and resource: returning current gas prices for EVM chains, broken out by slow/standard/fast and adding trend analysis. It is immediately distinguishable from the sibling tools, none of which cover gas price 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?

The description implies a clear trigger: use this when current EVM gas prices or gas trends are needed. It does not explicitly name alternatives or exclusions, but the sibling list contains no competing gas tool, so the usage context is sufficiently clear.

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

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

With no annotations provided, the description carries the behavioral transparency burden and does meaningful work: it discloses that data is 'cached,' that it is refreshed every 15 minutes, and that the call 'Returns' data rather than mutating state. This gives the agent a clear read-only mental model. It does leave 'registry enrichment' and the meaning of 'top' somewhat undefined, but the core behavior is transparent.

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

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

Three sentences, each serving a distinct purpose: core operation, filter options, and returned data plus freshness. The main purpose is front-loaded and 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?

For a read-only query tool with 8 optional parameters and no output schema, the description covers purpose, filters, return fields, and data freshness. It does not explain pagination behavior or whether filters combine, but the schema documents defaults, limits, and enums, so the agent has enough to invoke the tool correctly.

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

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

The input schema already documents all 8 parameters with descriptions and enums, so the baseline is 3. The description adds useful examples for protocol, chain, and token filters, and the return metrics (TVL, APY, volume) map naturally to the sortBy enum. However, it does not add meaning beyond the schema for pool, limit, offset, order, or sortBy.

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 opens with a specific verb and resource: 'Get a cached snapshot of top DeFi liquidity pools.' It also lists the available filters and the key returned metrics, making the tool's scope clear. It does not explicitly distinguish itself from sibling tools, but the pool-specific focus and return fields separate it from the token- and transaction-oriented siblings.

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

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

The description implies the tool is for querying current pool snapshots and filtering by protocol, chain, or token, but it provides no explicit when-to-use or when-not-to-use guidance. It never mentions alternatives or contrasts with sibling tools such as token_research, registry_lookup, or token_intel, leaving routing decisions to the agent.

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 must carry behavioral context, and it does disclose return fields and that no payment is required. However, it does not state whether the operation is read-only, whether auth is needed, error behavior, or rate limits. It is adequate for a simple lookup but not richly transparent.

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 concise sentences with the action and return values front-loaded. The cost note is short and useful. 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?

For a simple two-parameter lookup with no output schema, the description names all key return fields so an agent knows what to expect. It could mention behavior when an address is not found or unsupported, but the essentials for invoking it correctly are present.

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

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

Schema description coverage is 100%, so the schema already explains both parameters fully. The description adds no meaning beyond what 'Contract address (0x-prefixed)' and 'Blockchain network' already provide, 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 action and resource: 'Look up a contract address in the Known Contract Label Registry.' It also lists the returned fields (protocol name, category, risk level, tags), making the function clear. It does not explicitly distinguish this from sibling tools, so it doesn't earn 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 guidance on when to use this tool versus alternatives, nor any exclusions or conditions. The 'Free' note addresses cost, not selection context. An agent gets no help choosing between registry_lookup and sibling tools like token_risk_metrics or contract_monitor.

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 burden. It clearly describes an analysis operation and enumerates the return fields (score, confidence, label, reasoning, per-entity sentiment). It does not explicitly state there are no side effects, but the read-only nature of a sentiment analyzer is strongly implied by the description and name.

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

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

The description is a single concise sentence that front-loads the core action and resource, then immediately lists the output contract. Every part is informative and there is no 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 no output schema present, the description correctly takes on the job of describing return values, and it covers score range, confidence, label range, reasoning, and per-entity output. The input parameters are fully covered by the schema, so an agent has enough context to call the tool correctly.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds context about the four contexts and output meaning, but does not substantially extend what the schema already documents for the text and context parameters.

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

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

The description states a specific verb ('Analyze sentiment of text') and resource, and lists the supported contexts. It is unique among the sibling tools, so an agent can clearly distinguish it from other operations like summarize or tx_decode.

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

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

The description implies when to use the tool: whenever sentiment analysis is needed for text in crypto, finance, social media, or general contexts. It does not explicitly state when not to use it or name alternatives, but none of the siblings perform sentiment analysis, so the usage context is clear.

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 must carry the behavioral burden. It adds some useful behavior context by naming the return fields and noting that no payment is required, but it does not mention error behavior, rate limits, or the read-only nature of the lookup.

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

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

The description is two short sentences, front-loads the core action, and contains no redundant fluff. The free-access note is brief and useful.

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

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

For a single-parameter lookup tool with no output schema, the description is mostly complete: it identifies the input, the registry, and the expected outputs. Missing explicit sibling-differentiation guidance keeps it from being fully complete.

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

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

Schema description coverage is 100%, so the schema already documents programId as a Base58 Solana program ID. The description adds little beyond restating that the parameter is a Solana program ID.

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

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

The description uses a specific verb and resource: 'Look up a Solana program ID in the program label registry.' It also states the output fields, distinguishing it from sibling tools focused on transactions, tokens, or wallets.

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

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

No guidance is given about when to use this tool versus alternatives like registry_lookup or solana_token_risk_scan. The only contextual addition, 'Free — no payment required,' addresses cost rather than usage conditions.

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

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

With no annotations, the description carries the behavioral burden. It does disclose the analysis dimensions and the risk-score output, implying a read-only analytical scan. Still, it does not explicitly state that it never writes/transacts, how data is sourced, or what limitations the risk score has.

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

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

The description is a single front-loaded sentence: it opens with the core purpose and then packs the key checks and output scale into a compact, readable list. Every phrase carries meaning and there is no filler.

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

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

The description gives enough high-level information to know the tool exists and what kind of output to expect, but without an output schema or annotations it under-specifies the exact return fields and the risk score's calculation basis. It also does not disambiguate from other risk-related sibling tools.

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

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

The schema fully describes the single 'mint' parameter as a Base58 Solana token mint address, so the description does not need to repeat it. The description adds no constraint or nuance beyond the schema, which matches the baseline for high schema coverage.

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

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

The description clearly states the tool performs a Solana token rug check and enumerates concrete checks: mint/freeze authority, holder concentration, liquidity depth, and a 0-100 composite risk score. It is not a tautology and gives a specific resource and outcome, but it does not distinguish itself from nearby siblings like token_risk_metrics or token_intel.

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 'rug check' phrasing implies the tool is meant to assess whether a Solana token may be a rug pull, which provides implicit usage context. However, there is no explicit guidance about when to choose this tool over competing siblings or when it should not be used.

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

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

With no annotations present, the description carries the behavioral burden; it discloses what the tool returns (labeled programs, token/SOL movements, success status, risk flags). This is genuinely informative, though it does not explicitly state read-only behavior or error conditions.

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

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

A single sentence with the primary verb and resource front-loaded, followed by a compact list of output categories. Every phrase earns its place; no filler or repetition of schema 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 one-parameter, read-oriented explainer, the description is largely sufficient: it names the required input and the main output facets. However, it omits any mention of error cases (invalid signature, unsupported transaction types) or limitations compared with simulation, so it is not quite fully complete.

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

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

The sole parameter signature is already documented in the schema as a Base58 Solana transaction signature, giving 100% schema coverage. The description adds no additional parameter-level context, so the baseline of 3 is appropriate.

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

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

Starts with a specific verb ('Explain') and resource ('Solana transaction'), and enumerates the concrete outputs (labeled programs, token/SOL movements, success status, risk flags). This clearly distinguishes it from sibling tools like tx_decode or solana_tx_simulate by emphasizing a human-readable interpretation.

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 explicit guidance about when to choose this over closely related siblings such as tx_decode, solana_tx_simulate, or solana_token_risk_scan. The phrase 'plain English' implies it is for human-readable explanations, 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 full responsibility. It discloses that simulation produces balance changes and a recommendation, implying a non-mutating operation, but it does not explicitly state that no on-chain effect occurs, nor does it mention permissions or rate limits. Given the absence of annotations, this is adequate but not exhaustive.

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

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

The description is a single, front-loaded sentence that lists key outputs without fluff. Every phrase contributes to understanding the tool's purpose and results.

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 one parameter, no output schema, and no annotations, the description adequately explains what the tool does and what it returns (balance changes, labeled programs, risk rules, recommendation). It could clarify the format of the recommendation or specify determinism, but overall it is sufficient for an agent 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?

The sole parameter 'transaction' is fully described in the schema as 'Base64-encoded unsigned (or signed) Solana transaction', and the tool description adds no additional meaning beyond that. Since schema coverage is 100%, the baseline is 3; no extra context is provided.

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

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

The description clearly states a specific verb ('Simulate') and resource ('Solana transaction'), and enumerates concrete outputs (balance changes, labeled programs, risk rules, recommendation). It distinguishes from siblings like solana_tx_explain (explains) and tx_decode (decodes) by emphasizing pre-signing simulation.

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

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

The phrase 'before signing it' provides a clear temporal context for when to use the tool. However, it does not explicitly state when not to use it or compare to alternatives, though the sibling list suggests other transaction-related tools that could be used instead.

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 behavioral burden. It does disclose the return shape (summary, key points, compression ratio), but it does not state whether the operation is side-effect-free, whether it has input limits, or any behavioral caveats beyond the schema.

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

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

The description is a single dense sentence that front-loads the core action, lists the relevant options in order, and closes with the output. There is no filler or redundant detail.

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 compensates by naming the returned artifacts (summary, key points, compression ratio) and by enumerating all configurable modes. It falls slightly short of a 5 because it omits any usage context or behavioral caveats, but it is largely sufficient for a non-destructive summarization 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%, so the baseline is 3. The description mainly restates the enum values and optional focus that appear in the schema, adding little semantic meaning beyond what is already structurally documented.

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

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

The description clearly identifies the verb ('Summarize'), the resource ('text'), and the key configurability (length, format, focus). It also differentiates itself from sibling tools like translate and sentiment by specifying output artifacts (summary, key points, compression ratio).

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

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

The description gives no guidance on when to use this tool versus alternatives or when not to use it. There are no exclusions, prerequisites, or sibling-tool comparisons, leaving the agent to infer suitable contexts from the tool name alone.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It states what the call returns (full research, abbreviated metrics, AI analysis) which covers the primary behavioral effect. It does not claim any side effects, and the read-only nature is clearly implied. It does not mention rate limits or authentication, but for a research tool that is usually not necessary. The description adds sufficient transparency beyond the raw schema.

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

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

The description is two tight sentences. The first sentence states the action and bound, the second enumerates the output. Every clause earns its place; there is zero fluff. It is also front-loaded with the core purpose before details.

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 read-only comparison tool with no output schema and no annotations, the description covers the key aspects: what input it takes (primary + comparisons) and what output it produces. It does not clarify whether token identifiers are addresses or symbols, but the schema also leaves that open, so the description is not uniquely deficient. Given the tool's simplicity, this is close to 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 every parameter already has a description (e.g., 'Primary token to research', 'Tokens to compare against (1-3)', 'Blockchain network'). The tool description merely rephrases the primary/compare roles ('primary token', 'up to 3 others') and does not add new meaning beyond what the schema already provides. Thus the baseline score 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 opens with a specific verb ('Compare') and a clear resource ('a primary token against up to 3 others'). It explicitly states the output mix (full research on primary, abbreviated metrics on comparisons, AI comparative analysis), which neatly distinguishes it from single-token siblings like token_research or token_intel. No ambiguity about what this tool does.

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 makes the use case obvious: use when you need a comparison across multiple tokens. However, it does not explicitly say 'for single-token deep dives use token_research' or otherwise state when NOT to use this tool. The context is clear but lacks explicit exclusions or alternative routing, so it misses the top bar.

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

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It implies a read-only operation ('lookup') but does not explicitly confirm safety, rate limits, or side effects. It claims 'any EVM or Solana token', yet the chain enum is limited to five chains (ethereum, base, solana, polygon, arbitrum), which is a scope mismatch that is not disclosed. The phrase 'basic risk assessment' leaves what that entails undefined, and there is no mention of output format or potential errors.

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

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

The description is a single sentence that is concise and front-loaded with the core purpose. Every word earns its place; there is no filler or redundant phrasing.

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

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

Given the large set of sibling tools, the description is incomplete for an agent to choose correctly. It does not explain what 'basic risk assessment' entails, which chains are actually supported (despite saying 'any EVM'), or what the return structure looks like. There is no output schema, so the description should clarify the response format, but it does not. An agent could easily confuse this with token_research or token_risk_metrics.

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

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

Schema coverage is 100%, so the baseline is 3. The description does not add any parameter-specific meaning beyond the schema; it lists output fields rather than clarifying the input parameters. The address description in the schema already mentions 'Token contract address or name', and the chain enum is self-explanatory. No extra semantics are provided.

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

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

The description states a specific verb ('lookup') and resource ('token') and lists the fields returned (price, market cap, volume, basic risk assessment). It positions itself as 'lightweight', which hints at a lighter alternative to heavier tools, but it does not explicitly differentiate from siblings like token_research or token_compare. The purpose is clear but not sharply delimited.

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

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

The description gives no explicit guidance on when to use this tool versus the many token-related siblings (e.g., token_research, token_compare, token_risk_metrics). It implies a quick check through the word 'lightweight', but does not state conditions like 'use for a quick snapshot, use token_research for deep analysis'. No exclusions or alternatives are named.

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?

There are no annotations, so the description carries the transparency burden. It does disclose that the tool aggregates data from CoinGecko, DeFiLlama, Etherscan, and Polymarket and includes AI risk assessment, which adds useful context. However, it reveals nothing about read-only behavior, permissions, latency, failure modes, or response handling for a potentially complex multi-source operation.

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

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

The description is compact and front-loaded with the core purpose, followed by a source list. It wastes no words, though the opening noun phrase 'Multi-source token intelligence' is somewhat generic and the long enumeration could be better structured.

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

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

For a complex aggregator with no output schema and no annotations, the description gives a useful high-level map of capabilities and sources but lacks important completion details such as expected output shape, module-to-source mapping, error behavior, or limitations. It is sufficient for basic tool selection, not for fully anticipating invocation 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 100%, so parameters (query, chain, include) are already documented. The description adds no additional parameter-level detail such as accepted query formats, chain behavior, or how the include modules map to output sections. Baseline 3 is appropriate because the schema carries the load.

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 (token intelligence) and enumerates concrete modules (market data, DeFi metrics, contract verification, prediction markets, holder analysis, price history, AI risk assessment) plus the aggregated sources. It is clear about the tool's broad scope, but it does not explicitly distinguish it from closely named siblings like token_intel or token_risk_metrics.

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

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

No guidance is given on when to choose this tool over the many similar sibling tools. The description implies it is a general multi-source token research tool, but it never states when to use it versus token_intel, token_compare, token_risk_metrics, or solana_token_risk_scan.

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

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

With no annotations provided, the description carries the behavioral disclosure burden. It discloses that results are pre-computed for top tokens and live-computed for others, which implies possible latency differences, and it clearly enumerates what the risk assessment includes. It does not mention output format or error behavior, but the operation is inherently read-only and low-risk.

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

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

The description is two sentences with no filler. The first sentence front-loads the tool's purpose and metric list, and the second adds a meaningful performance/availability distinction. Every phrase contributes 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?

The metric list gives a strong sense of what the agent will receive, but there is no output schema and the description does not explain the return structure, weighting methodology, or failure cases such as unsupported tokens. It is adequate for invoking the tool correctly but leaves some uncertainty about the response shape.

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

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

Schema description coverage is 100%, so both 'address' and 'chain' are already well documented in the schema. The description adds no additional parameter-level meaning, but the baseline of 3 is appropriate because the schema fully handles parameter semantics.

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

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

The description clearly states the tool computes quantitative risk metrics for ERC-20 tokens and enumerates the specific dimensions: holder concentration, contract permissions, liquidity depth, deployer history, and a composite risk score. This is specific enough to distinguish it from broad tools like token_research or token_intel and from the Solana-specific sibling.

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

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

The description gives useful context such as 'for any ERC-20 token' and distinguishes pre-computed vs live-computed behavior, but it does not explicitly state when to prefer this tool over related siblings like token_intel or token_research. Usage is implied rather than explicitly guided.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It mentions important behaviors: auto-detection of source language, preservation of formatting and cultural nuances, and tone control. However, it does not specify whether the operation is read-only or has side effects, nor does it mention rate limits, authentication, or error behavior such as failures for unsupported languages. For a translation tool that likely makes external API calls, this is a moderate 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?

The description is a single, concise sentence of about 25 words, with each clause earning its place. It front-loads the primary action ('Translate text to any language') followed by key features (tone control, auto-detection, formatting preservation). No filler or redundancy; it is easy to parse quickly.

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

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

Given the tool has 4 parameters, 2 required, and no output schema, the description covers the core function but leaves some gaps. It doesn't explain the return format (e.g., translated text only or also detected source language), which could be important for an agent to parse the result. It also doesn't mention limitations like unsupported languages or maximum input length, though the schema hints at a 20,000 character limit. The description is sufficient for basic use but could be more complete for error handling and response parsing.

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

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

The schema description coverage is 100%, so all four parameters (text, tone, sourceLanguage, targetLanguage) have descriptions in the schema. The tool description adds context about tone control and auto-detection, which maps to the 'tone' and 'sourceLanguage' parameters. However, it doesn't add details about the format of the 'text' parameter (e.g., encoding) or the exact format of 'targetLanguage' (though the schema gives an example). The description complements the schema adequately but doesn't significantly enhance understanding beyond what the schema already provides.

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

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

The description clearly states the tool's purpose: 'Translate text to any language with tone control' and lists specific tone options. It also mentions auto-detection of the source language and preservation of formatting and cultural nuances, which clearly distinguishes it from sibling tools like 'summarize' or 'sentiment' that perform different text processing tasks.

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

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

The description implies when to use it (any translation task) but does not explicitly state when not to use it or mention alternatives among the listed sibling tools. Since there are no obvious translation siblings in the list, the lack of explicit exclusions is a minor gap, but the purpose is clear enough that an agent would know to use it for translation needs.

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

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

With no annotations, the description carries the burden of disclosing behavior. It does say what the output will contain, which is useful, but it does not mention error cases, unsupported transaction types, or whether the operation is purely read-only. The 'any' claim is also broader than the six-chain schema enum implies.

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

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

A single sentence that front-loads the core action and packs the output summary into a tight colon-delimited list. 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?

For a two-parameter tool with no output schema, the description gives a useful high-level output summary, and the schema covers the inputs. However, it does not address invalid hashes, unsupported networks, or the actual response format beyond the list of decoded content, leaving some runtime ambiguity.

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

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

Schema description coverage is 100% and both parameters have descriptions, so the baseline is 3. The tool description adds no parameter-specific meaning beyond the schema; it focuses on output, not 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?

Description has a specific verb ('Decode') and resource ('any EVM transaction') and enumerates output ('function call, parameters, token transfers, and plain-English explanation'). The EVM qualifier clearly distinguishes it from the Solana-oriented siblings such as solana_tx_explain.

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 context of use is implied by 'Decode any EVM transaction', but the description does not explicitly state when to prefer this tool over alternatives or when not to use it. It names no sibling tools and gives no exclusions or boundary conditions.

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

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

With no annotations present, the description carries the full behavioral burden and largely delivers: it discloses what the scan covers, the return contract (risk score 0-100, risk level, action items, service suggestions), and supported chains. It stops short of edge behaviors such as latency implications of 'deep' scans, failure modes for unsupported address formats, or what 'related service suggestions' actually are.

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

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

Three sentences, each earning its place: purpose in the first, return shape in the second, and chain support in the third. The core action is front-loaded with zero 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?

For a 4-parameter tool with no output schema and no annotations, the description covers purpose, behavioral scope, the return contract, and chain coverage — enough for an agent to call it correctly. Missing elements are usage routing versus siblings and depth/latency expectations, which are useful refinements rather than blockers.

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

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

Schema description coverage is 100%, so the baseline of 3 applies; the description adds little parameter-level value beyond the schema. The closest overlap is 'assesses target contract risk,' which mirrors the targetContract parameter that the schema already documents fully.

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 pairs a specific verb-resource ('wallet safety check') with three concrete analysis components — approvals, transaction activity, and target contract risk — that clearly differentiate it from narrower siblings like approval_scan (approvals only) and solana_token_risk_scan (token risk only). The 'Comprehensive' framing plus the composite output shape establishes it as the umbrella safety tool.

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

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

Usage is implied through scope rather than stated: the breadth of the checks signals 'use this when you need the full wallet picture,' but the description never names alternatives, exclusions, or conditions (e.g., 'for approvals-only, use approval_scan instead'). An agent must infer routing against several overlapping siblings.

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