Token Safety (Base)

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

With no annotations, the description carries the full burden and does meaningful work: it discloses the economic model ($0.02 via x402) and the shape of the analysis (typed holders, concentration, bundling). It leaves failure modes, rate limits, and confirmation of read-only/non-mutating behavior unstated.

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

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

Two tightly packed sentences: analysis scope first, usage and price after. No filler, and the most decision-relevant information is 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?

No output schema exists, and the description compensates by enumerating the returned elements (typed top-10 holders, concentration, distribution, bundling). That is sufficient for a single-parameter read-only analytical tool, though it stops short of describing response format or defaults beyond the schema's own note.

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

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

Schema coverage is 100% for the single address parameter, including the pattern and the AERO-example fallback when omitted, so the schema already does the heavy lifting. The description adds nothing about the parameter, which is the expected baseline when coverage is complete.

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 with scope: holder analysis for an ERC-20 on Base, enumerating what is produced (top 10 holders typed wallet/contract/LP/burn, concentration, distribution, bundling). It does not explicitly differentiate from siblings like rug_check or token_risk, which likely also touch supply concentration.

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?

"Use to judge supply concentration" gives a clear context for selecting this tool over generic token analysis. However, it names no alternatives (rug_check, token_risk) and states no exclusions or prerequisites, so the routing is implied rather than explicit.

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

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the output range, the low/medium/high confidence grading, the null-for-stablecoins case, and the $0.02 x402 payment requirement. It omits rate limits, latency, and error behavior, and does not repeat the schema's default-example fallback.

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 sentences, front-loaded with the score range and resource, each carrying distinct information (scope, inputs, null case, use case, price). Slightly telegraphic phrasing but 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?

No output schema and no annotations, so the description must explain results, and it does convey score range, confidence levels, and null semantics. Cost and its Base/ERC-20 scope are covered; permissioning and failure modes are the only real 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% and the single address parameter is fully documented there, including the AERO-example fallback. The description adds the underlying metrics (24h volume, volume vs liquidity, price change) but those are algorithm inputs, not parameter syntax, so the baseline of 3 applies.

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

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

States a specific computed resource ('momentum score 0-100 for an ERC-20 on Base') and even its inputs, which is well beyond a tautology. It never names a sibling, though, so the agent must infer the activity-vs-risk split against holder_check/rug_check/token_risk on its own.

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?

'Use to rank Base tokens by activity' gives a concrete context for selecting this tool, and 'Null for stablecoins' sets a boundary on useful inputs. No alternative tool or when-not condition is named, so it falls short of full routing guidance.

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

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

With no annotations, the description carries the full behavioral burden, and it does disclose two useful non-schema facts: the cost/payment mechanism ($0.02 via x402) and the enumerated output signals. It omits any mention of latency, rate limits, data freshness, or what a low-confidence verdict should mean to the caller.

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

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

Two sentences, zero filler: the first front-loads what it returns, the second gives the calling context and the price. Nothing redundant against the schema or title.

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

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

For a single-parameter tool with no output schema, the description is nearly self-sufficient: it names the chain, the asset class, the verdict fields, and the payment model. It stops just short of explaining how to interpret 'confidence' or the five signals, which an agent would need to act on the result.

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

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

Schema description coverage is 100% and the single optional 'address' parameter is fully documented in the schema, including the example-fallback behavior when omitted. The description adds no parameter-level detail beyond that, so the baseline of 3 applies.

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

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

States a specific verb+resource ('rug-pull check for an ERC-20 on Base') and even enumerates the return shape (rug_pull true/false, confidence, 5 named signals), which is unusually concrete. It does not differentiate itself from siblings like token_risk, token_verdict, or token_safety_demo, which appear to overlap on the same chain/token-risk space.

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?

'Use before buying a new Base token' gives one clear use context, which is more than nothing. However, with four semantically adjacent siblings (token_risk, token_verdict, token_safety_demo, holder_check) in scope, the absence of any when-to-use-this-vs-that guidance is a real gap.

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

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the cost model ($0.02 via x402), the direction of the score (higher = riskier), the exact signals measured, and a scope/liability caveat. It omits auth requirements, rate limits, and how long a score stays valid, but the core behavioral profile is clear.

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 score range and direction, then factors, then usage trigger, then price and disclaimer. Every clause carries information; nothing is redundant.

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

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

With no output schema, the description compensates by explaining the score scale and the constituent signals. It does not describe the response shape (field names, whether the flags are booleans or sub-scores), so an agent knows what the number means but not exactly what it receives.

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

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

There is a single optional parameter with 100% schema description coverage, including the AERO fallback and example=true behavior. The description adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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

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

The description states a specific resource (ERC-20 token on Base) and output (0-100 risk score) plus the exact factors scored: liquidity, top-5 holder concentration, honeypot/tax flags. It does not, however, differentiate itself from sibling tools like rug_check or token_verdict, which appear to cover overlapping risk-assessment ground.

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?

'Use before buying or listing an unknown Base token' gives a clear triggering context for the tool. It stops short of naming alternatives (e.g. rug_check, token_verdict) or stating when this tool should be skipped, so the agent must infer routing from names 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 and does well: it discloses a hard rate limit (5 calls/day per IP), that no payment/auth is required, and that output matches the paid tool. It does not explain quota-exceeded behavior or error responses, but the core behavioral traits are surfaced.

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 a parenthetical; the free-demo framing and quota are front-loaded, and there is no redundant or filler 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 dispatcher with no annotations and no output schema, the description covers the key facts an agent needs: quota, cost, tool choices, and output parity with the paid versions. Remaining details (quota-exceeded errors, per-tool return differences) are minor 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 both the 'tool' enum and the 'address' pattern plus the AERO-example fallback. The description restates the tool enum values but adds no syntax or format detail beyond what the schema provides, so baseline 3 applies.

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

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

The description names a concrete action (run one of five named analysis tools) and pinpoints the tool's role as a free demo wrapper around the paid siblings. It distinguishes itself from the sibling tools by the demo/quota framing, though a reader must infer from the tool list exactly how this proxy relates to each 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?

It clearly states the conditions for use: free, 5 calls/day per IP, no payment, and enumerates which tools can be invoked. It lacks explicit when-not guidance (e.g., what to do once the quota is exhausted, or when to switch to the paid equivalent).

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

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

With no annotations, the description carries the full burden and does well: it discloses the payment requirement ($0.05 via x402), the exact output categories (avoid / high_risk / caution / low_risk) with a one-line summary, and a liability disclaimer. It does not mention latency, rate limits, or whether results are cached, but the safety/payment profile is unusually well covered for an unannotated 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?

Three dense sentences: capability, usage trigger, then cost/disclaimer. The verdict vocabulary and the use-case trigger are front-loaded, and every clause carries information (checks performed, output categories, price, legal caveat) with no filler.

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

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

No output schema exists, so the description must convey the return value, which it does by naming the four verdict tiers and the accompanying English summary. Combined with the schema's documentation of the address parameter and its example fallback, an agent has everything needed to call and interpret this tool.

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

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

Schema description coverage is 100% and the single address parameter is fully documented in the schema, including the example fallback behavior. The description adds only the 'ERC-20 on Base' framing, which the schema already implies, so the baseline 3 applies.

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

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

Names a specific resource (ERC-20 on Base) and a specific action (one-call verdict) and enumerates the constituent checks (risk, rug-pull, holder, momentum, contract flags) plus the exact verdict vocabulary it returns. This clearly positions it as the aggregator relative to the narrower siblings holder_check, momentum_score, rug_check and token_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?

'Use once before buying or listing an unknown Base token' gives an explicit decision context, and 'one-call' implicitly contrasts with invoking the four sibling checks separately. It stops short of stating when NOT to use it (e.g. known/safe tokens, non-Base chains) or naming the siblings as alternatives, so it is clear but not complete.

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