AgentFlow

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

No annotations provided, so the description is the sole source. It implies a read-only query by describing distinct agents active over windows, but does not disclose data update frequency, authentication needs, or potential side effects. Adequate but not rich.

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

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

A single sentence using metaphor, economical with words. However, the metaphor might slightly obscure clarity. No wasted 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?

Given no parameters, no output schema, and no annotations, the description explains the core metrics but omits output format (e.g., numbers, data structure). Sufficient for basic understanding but lacks precision.

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?

No parameters exist, so the description need not add param info. Baseline 4 per 0-param rule. No param details are missing.

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 'speedometer' metaphor to indicate it measures active AI agents on Base in live 24h/72h windows versus cumulative count. It clearly states the resource and scope, but doesn't explicitly differentiate from sibling tools like 'index_stats' or 'real_agent_index'.

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

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

No guidance on when to use this tool versus alternatives. It only describes what it returns, leaving the agent to infer appropriate contexts without comparison to sibling tools.

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

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

No annotations exist, so the description must disclose behavioral traits. It explains the output components (wash, hub, automation score, labels) but does not mention if the tool is read-only, rate limits, or authentication needs. This is adequate but not comprehensive.

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 packs key information (range, categories, components) efficiently. It is front-loaded with the core purpose. Slightly structured formatting (e.g., listing components) would improve readability.

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 detailing the return format (score range, category labels, and components). For a simple one-parameter tool, this covers the essential aspects, though it omits error cases or usage context.

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 'address' is described in the schema as '0x... Base wallet address'. The description adds no additional semantics beyond that. With 100% schema coverage, baseline 3 is appropriate.

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

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

The description clearly states the tool returns a counterparty risk score with a specific range (0-100) and categories (LOW/MEDIUM/HIGH/UNKNOWN), along with additional details like wash/hub detection and labels. This is distinct from sibling tools like screen_wallet or agent_pulse, which focus on different analyses.

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 provided on when to use this tool versus alternatives like screen_wallet or real_agent_index. The description does not specify prerequisites, limitations, or contextual triggers for invoking the tool.

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 bears the full burden of disclosing behavioral traits. It does not state side effects (though likely none), required permissions, or data freshness. The list of stats provides some transparency about output content, but lacks details about real-time vs. cached 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?

The description is a single, well-structured sentence that front-loads the core purpose ('AgentFlow coverage stats') and then lists relevant items. No excess verbiage or repetition.

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

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

Despite no output schema, the description only names categories without specifying their format (e.g., counts, lists, booleans). An agent needs to know whether 'wallets tracked' is a number or a list of wallet IDs. This lack of structure reduces completeness.

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 has zero parameters, so schema coverage is effectively 100%. Baseline is 4, and the description adds no parameter info, which is acceptable as none is needed. The description does not hinder understanding of 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?

The description clearly indicates the tool returns 'AgentFlow coverage stats' and lists specific categories such as wallets tracked and agents labeled. However, it lacks an active verb like 'retrieve' or 'get', which would strengthen clarity. It is sufficiently specific to distinguish from sibling tools like real_agent_index or agent_pulse.

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

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

The description provides no guidance on when to use this tool versus the siblings. It does not mention any prerequisites, context where it is appropriate, or alternatives. The agent must infer usage from the listed stats 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 carries the full burden. It does not disclose behavioral traits such as data source, update frequency, or side effects (though it is clearly read-only).

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, but the second phrase 'The honest benchmark' adds slight redundancy. Still concise and front-loaded.

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

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

For a tool with no parameters and no output schema, the description is adequate but lacks details on the output format (e.g., numeric percentage range) or how to interpret the result.

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

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

There are no parameters, so the description does not need to add meaning beyond the schema. Baseline 4 applies.

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

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

The description clearly states the tool's purpose: measuring the percentage of AI agent USDC flow on Base that is wash/self-dealing vs. genuine. It is distinct from sibling tools like agent_pulse or counterparty_risk.

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

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

The description implies usage (when you need this specific metric) but provides no explicit guidance on when to use this tool versus alternatives or when not to use it.

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

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

With no annotations, the description must disclose behavioral traits. It mentions the output structure (score, confidence, reasons) but omits details like whether the operation is read-only, any side effects, or prerequisites. The agent is left guessing about potential impacts.

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

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

The description is two sentences, front-loaded with the tool's purpose and output. Every word adds value, with no redundancy or unnecessary 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?

Given the tool's moderate complexity and lack of output schema, the description covers the input, output, and usage context. However, it could benefit from clarifying the score interpretation or the nature of the screening process to fully prepare the agent.

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 'address' is already described in the schema as '0x... Base wallet address', which covers its meaning. The description reinforces 'any Base wallet' but adds no new semantic value beyond the schema, meeting 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 screens Baset wallets for sybil behavior, returning a score and reasons. The verb 'screen' and explicit output details make purpose clear. However, it does not differentiate from siblings like counterparty_risk, which may overlap.

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 includes a usage hint ('Use before an agent trusts or pays a counterparty'), providing context. However, it does not explicitly state when not to use or compare to alternatives like counterparty_risk.

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

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

With no annotations, the description carries full burden. It discloses key behavioral traits: the result is a lower bound, derived from receipts, methodology-versioned, and blind spots are disclosed. It does not cover auth or rate limits, 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?

The description is two concise sentences, front-loading the core purpose and metrics. Every word adds value, with no redundancy. Perfectly structured for quick understanding.

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

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

Given no output schema, the description explains the returned metrics and methodological provenance. It could mention output format or how to interpret chain coverage %, but is sufficient for a parameterless 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?

There are no parameters, so the schema provides no meaning. The description does not need to add parameter details. Baseline 4 applies, as the description focuses on what the tool outputs instead.

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 provides a daily verifiable lower bound settlement tape for x402-style USDC on Base, listing specific metrics (tx count, volume, wash-suspect share, etc.). It distinguishes from siblings by specifying a niche focus on x402 settlement, not general stats.

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 includes 'NOT total x402 volume' and mentions blind spots, implying it's a cautious lower bound. However, it does not explicitly state when to use this tool versus sibling tools, leaving usage context largely implied.

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