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

With no annotations, the description carries the full burden and delivers: the list is ranked and capped, a `partial` answer is a floor rather than the complete set, degree figures are lower bounds, unlabelled counterparties are explicitly NOT people, and non-interacting addresses are simply absent. These are exactly the caveats an agent needs to avoid over-reading results.

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 purpose statement followed by tight mode bullets, with the capping caveat last. Every sentence earns its place, though the mode formatting is dense for a definition of this length.

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 an 11-parameter tool with no annotations and no output schema, the description covers mode selection, result capping, and interpretation caveats. It stops short of describing the shape of the returned counterparty records or how `since`/`until` windows interact with the 'lower bound' claim.

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 91%, so the schema already documents nearly every parameter, including the `rank_by` value-vs-tx_count tradeoff and the `direction` default. The description adds mode semantics and the capping caveat, which is useful but largely overlaps what the schema already supplies.

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 opening line states a specific verb and resource ('Who a wallet dealt with and for how much'), and the three named modes carve out precise sub-purposes. It never names the siblings screen_address or trace_funds, so an agent must infer the boundary from function alone rather than being told.

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?

Each mode is given an explicit question it answers, including the exact user phrasing it targets ('which ordinary people funded this wallet') and the precondition for `check` ('you already have suspect addresses'). It also rules out mode combination ('the modes do not combine').

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 does so well: it discloses that `sanctioned: true` is blocking independently of score, that the score is a 0–100 risk reading rather than a share of funds, that absent addresses are reported as NOT FOUND and must not be treated as clean, and that chain is identity rather than a hint. These are meaningful operational and interpretive traits beyond what the schema alone provides.

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 front-loaded with purpose then structured interpretation notes ('Read the answer this way') and chain semantics, with no filler sentences. There is mild redundancy with the schema's own chain description, which slightly limits conciseness.

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 and no annotations, the description does substantial work explaining return semantics, edge cases, and the meaning of chain omission. It remains incomplete only in tool-selection guidance against siblings and in any auth or rate-limit notes, which are not addressed.

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 baseline is 3, but the description adds real meaning: it stresses that chain is part of the address's identity, that the same 0x address is a different wallet on ethereum, bsc, and tron, and that omitting chain screens every allowed format with each result labelled. The schema already mentions omitting chain when unknown, so this is reinforcing and extending rather than wholly new.

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 ('screen') and resource ('one blockchain address'), and enumerates what it reports: risk level/score, sanctions, issuer freezes, address type, risk provenance, and supported chains. Clear purpose, but it does not differentiate from siblings trace_funds and list_counterparties, so an agent cannot tell from the description alone why to pick this over those.

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 by 'AML screening for one blockchain address' and the chain parameter guidance ('Pass chain when you know it; if you omit it...'), which helps a caller use it correctly. However, there is no explicit when-to-use/when-not-to-use guidance and no mention of the alternative sibling tools, so selection against trace_funds or list_counterparties is left to inference.

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 so: it discloses that the trail stops at labelled entities and high-degree service addresses, that the walk is bounded by wall clock so partial results are returned instead of a timeout, and that 'nothing found' can mean the budget ran out. These are non-obvious behaviors an agent must report honestly and could not infer from 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?

Front-loaded with the one-direction-at-a-time rule, then per-mode paragraphs, then the caveat paragraph. Slightly repetitive with the schema's direction description, but nearly every sentence carries 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?

No output schema exists, so the description must explain returns, and it does: it describes what the trail reports (exchange vs. dead end), that partial answers occur, and that the answer itself indicates which case it was. Complete for a 4-param tracing 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 schema already documents chain ambiguity, max_hops defaults and the bitcoin half-step, and the direction enum. The description restates direction semantics rather than adding syntax or constraints beyond the schema, so it sits at the baseline.

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 concrete verb-and-resource (trace an address's funding flows) and sharply separates its own two modes, incoming and outgoing. It never references the sibling tools (screen_address, list_counterparties), so an agent gets no help distinguishing this from them, which keeps it just below the top band.

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?

Explicitly says when each direction applies ('incoming walks funding backwards', 'outgoing follows the largest outgoing flows forward'), and adds the gating condition that outgoing requires an API key. It also frames the tool as lead-generating rather than exhaustive, telling the agent how to weigh the output.

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