publicaml

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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description's 'Read-only... never writes anything' restates that profile, and 'only lists existing on-chain counterparties' adds a little scope context, but there are no additional behavioral disclosures such as rate limits or pagination behavior. No contradiction with annotations.

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 short sentences, with the core action front-loaded, options in the middle, and the safety caveat at the end. Every clause adds information 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?

For a 5-parameter, 2-required tool with strong annotations and full schema coverage, the description plus schema is enough to know what to pass and what to expect conceptually. It does not specify return shape or ordering, but no output schema exists and the verb 'list' plus risk-field mention provides adequate context for a list operation.

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 describes all five parameters at 100% coverage, so the baseline is 3. The description repeats the category examples and the with_risk AML behavior already present in the schema descriptions, adding no genuinely new parameter meaning.

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 verb and resource ('List the counterparties an address has transacted with') and immediately identifies the optional category filter, which separates it from the sibling tools screen_address and trace_funds. The read-only note reinforces that this is a retrieval operation, not a mutation.

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 a clear context for when to call it (list an address's counterparties, optionally filtered and optionally with risk) but does not explicitly state when to choose screen_address or trace_funds instead. It has no exclusions or prerequisites but also no named alternatives.

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 cover read-only, idempotent, and non-destructive behavior; the description reinforces this with 'it only looks the address up, it never changes anything' and adds valuable return-shape detail (AML score, risk_level, category, sanctioned exposure, source-of-funds). No contradiction with annotations.

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 concise and front-loaded with purpose and return fields. The read-only sentence is somewhat redundant with the annotations but is brief and not distracting. Overall it is well-structured with minimal 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 only two fully documented parameters and no output schema, the description adequately covers what the tool returns, confirms it is read-only, and tells the agent this is the authoritative risk source. It does not discuss error cases or rate limits, but those are minor for such a simple lookup 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%, with both address and chain described and chain also having an enum. The description adds AML context but does not provide extra semantic detail beyond what the schema already supplies, so the 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 uses a specific verb and resource ('Screen a crypto wallet address for AML/KYT risk') and lists concrete return fields. It asserts it is the ONLY authoritative source for address risk, which helps distinguish it from web-searching, but it does not explicitly contrast with sibling tools trace_funds or list_counterparties.

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 gives clear usage context: use this tool to screen addresses for AML/KYT risk and do not guess or web-search instead. It does not provide exclusions or guidance on when to prefer sibling tools, so it stops short of a full 5.

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?

The description adds human-readable behavioral context beyond the annotations by explicitly saying it only reads on-chain history and never moves or changes funds. It also reveals what the report covers: exchanges, mixers, sanctioned wallets, and hop distance. It does not contradict the readOnlyHint, openWorldHint, idempotentHint, or destructiveHint annotations.

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 concise and front-loaded with the core purpose, followed by a compact safety clarification. Every sentence contributes useful information, and there is no filler, tautology, or unnecessary 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?

Given the strong annotations and fully documented schema parameters, the description provides enough context to invoke the tool correctly: what it traces, what it reports, and that it is read-only. The main gap is the lack of explicit guidance on how this tool relates to sibling tools and any coverage limitations implied by the openWorldHint annotation.

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%, with all three parameters already described. The description adds general context like 'hops' for max_hops and 'across the chain' for chain, but it does not add meaningful semantic information 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 states a specific action ('Follow') and a specific resource ('OUTGOING funds from an address across the chain'), then explains exactly what is reported: where funds end up (exchanges, mixers, sanctioned wallets) and how many hops away. This clearly distinguishes the tool from sibling tools like list_counterparties or screen_address by its tracing and endpoint-classification purpose.

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 clear: use this when you want to trace outgoing funds and see their destination categories and hop distances. It does not explicitly name alternative tools or state when not to use it, so it stops short of full explicit guidance, but the context is unambiguous.

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