Trust Check

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the read-only nature is covered. The description adds valuable behavioral context beyond annotations: the check covers specific risk categories, requires passing `from` to detect look-alikes, returns a verdict with reasons, and exposes a cost model (5 free checks/day, then $0.002 via x402). This is strong supplemental disclosure.

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

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

The description is three tightly packed sentences with no filler. The core usage directive is front-loaded ('Before sending crypto on Base, check the destination'), followed by concrete risk categories, parameter guidance, and pricing. Every sentence earns its place.

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

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

For a tool with no output schema, the description covers key operational details: what is checked, how to enable the poisoning check, what the return looks like, and the pricing model. It is slightly light on describing the exact verdict format, but the annotation set already covers read-only and open-world behavior, making the description adequate for selecting and invoking the tool.

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

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

Schema coverage is 100%, so the baseline is 3. The description additionally clarifies the real-world purpose of the `from` parameter by linking it to address poisoning ('pass `from` = your wallet'), which enriches the schema description. It does not mention `known` explicitly, but the schema already documents it, so no significant gap exists.

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 verb ('check'), the resource ('the destination' / address safety), and the specific scope (Base) in the first sentence. It enumerates distinct threat categories (scam blacklists, address poisoning, token contracts, burn addresses, never-used addresses) and explicitly says it returns a verdict with reasons, making the purpose unambiguous and distinct from the sibling check_token_safety.

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 an explicit when-to-use directive: 'Before sending crypto on Base, check the destination.' It also explains how to use the `from` parameter for the address-poisoning check. However, it does not explicitly contrast this tool with the sibling check_token_safety or state when not to use it, so a small guidance gap remains.

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

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

Annotations already declare readOnlyHint and openWorldHint, but the description adds material context they cannot carry: the rate limit (5 free calls/day), the paid fallback ($0.002 via x402 USDC on Base), and the verdict vocabulary. That cost and quota disclosure is genuinely useful for an agent deciding whether to call it.

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-loads the purpose, then the verdict enum, then pricing; every sentence carries information. Slightly dense but free of waste.

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 usefully enumerates the return verdicts (serial_collapser / collapsed_before / no_collapses_seen / unknown) and the underlying metrics, and it discloses billing. Complete enough for a single-parameter read tool.

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

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

Schema coverage is 100% and the single address parameter is fully documented with a pattern and label. The description restates the input as 'the wallet that deployed it' but adds no format or sourcing detail beyond the schema, 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?

States a specific verb (check) and resource (the wallet that deployed a newly launched Base token), plus the exact data returned: number of earlier tokens followed and how many collapsed. It is clearly distinct from siblings like check_token_safety and check_address_safety.

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?

Gives a clear situational trigger ('before buying a newly launched Base token'), which is exactly the decision point an agent would need. It does not explicitly name or exclude the sibling tools, so it falls short of a full when-not/alternatives statement.

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

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

Annotations only declare readOnlyHint and openWorldHint, but the description adds materially more: the detection heuristic (90%+ drop from peak = rug or dump), the ordering, and a real operational constraint — 5 free calls/day then $0.002 per call via x402 USDC on Base. Cost and rate-limit disclosure is exactly the kind of behavior an agent must know before calling.

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

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

Two sentences, no filler. The core definition and ordering are front-loaded, the usage line and the pricing caveat follow, and every clause (threshold, ordering, fields, price) carries information the 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?

There is no output schema, so the description carries the burden of describing the return — and it does: peak and remaining liquidity, hours from launch, creator wallet. Combined with the single well-documented parameter and the read-only annotation, nothing needed to call it correctly is missing.

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

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

Schema description coverage is 100%: the single `hours` parameter already documents its default (24) and 1–168 range. The description's phrase 'in the last hours' merely restates the window concept without adding format or edge-case guidance, 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?

States a specific resource (new Base tokens whose pool liquidity collapsed 90%+ from peak) plus ordering (newest first) and the returned fields. The signal is a market-wide collapse feed, which is clearly distinct from the sibling tools check_address_safety / check_token_safety / check_token_creator that evaluate one address or token at a time.

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?

Gives explicit intended uses: 'exit positions and blocklist serial creators', which tells the agent the decision context. It does not, however, name an alternative tool or state when this feed is the wrong choice (e.g. for vetting a single token before buying, where check_token_safety fits).

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