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

There are no annotations, so the description carries the full behavioral burden. It conveys that this is a read-only fetch, shows the identity document nature, and even discloses that agentId is null until registered. It does not mention error behavior, authentication, or rate limits, but the core behavior is reasonably 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?

Two sentences, no filler. The action and resource are front-loaded, the path format is given compactly, and the list of known names plus return fields are packed efficiently.

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 enum tool with no output schema, the description includes what to pass, the valid choices, and what the response contains. It does not describe error or not-found behavior, but the agent has enough context to call the tool correctly.

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 schema already documents the single name parameter with 100% coverage and an enum. The description adds the path pattern and the fact that these are BABA Capital agent-card names, but it does not add meaningful new semantics beyond the schema. 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 starts with a specific verb and resource: 'Fetch a BABA Capital ERC-8004 agent-card' and names the exact well-known path. It clearly states what the tool returns. It stops short of explicitly distinguishing itself from the sibling arc_agent_get tool, so it is not a full 5.

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 given about when to use this tool versus arc_agents_list, arc_agent_get, arc_agents_search, or other siblings. It lists valid names but provides no decision rules, exclusions, or alternative routing.

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 provided, the description carries the full burden. It discloses the return structure in detail (on-chain owner, agentURI, RAW card, validation report with evidence per flag) and explicitly mentions 'any fetch error' is included, which covers error handling. It doesn't explicitly state it's read-only, but 'get' implies non-mutating, and the description focuses on retrieval and validation.

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 dense sentence that front-loads the core content (full record) and then details components. It is efficient and packs relevant information without redundancy. Could be slightly more structured, but it's well within acceptable 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 a single-record retrieval tool with one parameter and no output schema, the description thoroughly explains what the response will contain, including the validation report's evidence details. It does not mention pagination (not needed for a single record) or any specific limitations, but the coverage is sufficient for an agent to know what to expect.

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 schema already describes agentId as 'The ERC-8004 agentId (an ERC-721 tokenId on the registry).' The description adds no additional semantics 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?

States a specific verb ('get'), a precise resource (full record for one Arc agent by agentId), and enumerates the returned content (owner, agentURI, RAW card, validation report with evidence). This clearly distinguishes it from siblings like arc_agents_list (list) and arc_agent_card (likely a simplified card view).

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 when-to-use instruction: 'Use this to check the directory's claims yourself rather than trusting them.' This implies the tool is for verification and deep inspection. It doesn't explicitly name alternatives or state when not to use it, but the sibling context and the phrase 'rather than trusting them' provide adequate 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 provided, the description must carry the full transparency burden. It discloses that data comes from a 'validated hourly crawl' (implying potential staleness) and that unresolved agents are 'listed as UNRESOLVED, never silently dropped' – a valuable behavioral guarantee. It also states the tool is 'Paged', but omits ordering/sort behavior and any rate-limit or error semantics, which is a minor gap. Overall, it provides meaningful context beyond 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?

The description is well-structured and front-loaded with the core purpose. It packs a lot of information – fields, statuses, filters, paging, and a behavioral note – into a compact, readable block. Every sentence serves a purpose, though it could be slightly tightened by moving the column list or status enumeration into a more terse form. No fluff or redundancy.

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?

The tool has no output schema, so the description must explain return values, and it does – listing the row fields (agentId, owner, agentURI, host, name, skills, status, x402, concentration). It also mentions pagination and the crawl freshness. Missing are ordering semantics and any error/edge-case handling, but for a filtered list tool this is largely complete. The omission of SKIPPED_ROBOTS in the status list is a minor completeness issue.

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 baseline is 3. The description adds a small grouping of parameters ('Optional filters: status, host, owner') and mentions 'Paged', which clarifies the role of limit/offset. However, it lists status values as 'OK | UNRESOLVED | INVALID', omitting 'SKIPPED_ROBOTS' which is a valid enum value in the schema – a potential source of confusion. This omission prevents the description from adding more value than 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 clear, specific purpose: 'List the ERC-8004 agents registered on Arc'. It names the resource (Arc agents) and the action (list), and it distinguishes itself from siblings like arc_agents_search and arc_agents_stats by the verb 'list'. The description also enumerates the fields returned, which reinforces its role as a broad listing tool.

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 does not explicitly state when to use this tool versus alternatives like arc_agents_search or arc_agents_stats. It implies listing and filtering via 'Optional filters: status, host, owner', but it never says 'use this for a broad overview' or 'use search for fuzzy queries'. No exclusions or alternative routing is provided, leaving the agent to infer the tool's niche from its name 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 provided, the description carries the behavioral burden. It adds important nuance beyond the schema: x402=true is a much smaller set than payment=true, and resolvable=true means the card actually fetched on the last crawl. That meaningfully shapes agent expectations, though it does not describe result format or side effects (which are unlikely for a search).

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 moves to parameter semantics, ending with the important caveat. All sentences earn their place and there is no filler, though the x402/payment sentence is dense and could potentially be tightened.

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 7-parameter search tool with no annotations and no output schema, the description covers the non-obvious filter semantics and purpose. It does not describe the result list shape or ordering, and since there is no output schema that would otherwise clarify returns, this is a minor gap that prevents a 5.

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 baseline is 3, but the description adds substantial meaning beyond it: it defines what q matches, what skill matches, and crucially distinguishes x402 from payment with a concrete example (USDC via ERC-8183 is not x402). This prevents a likely misinterpretation and makes parameter selection genuinely safer.

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 the specific verb and resource: 'Find an Arc agent that does something, and optionally one you can pay.' It is clear about what the tool does, but it does not explicitly contrast itself with sibling tools like arc_agents_list or arc_agent_get, so it stops short of a 5.

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 useful parameter-selection guidance: q matches name/host/skills while skill matches skill ids/names/tags, and it explicitly warns about the non-obvious x402 vs payment distinction. It does not directly name alternative sibling tools, so it is not a full 5, but the context is clear and excludes misuse on the most confusing filter.

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 provided, the description carries the full burden of behavioral disclosure. It states 'Facts only — the concentration numbers are stated so you can draw your own conclusion,' which clarifies that the tool returns raw metrics without interpretation or bias. However, it does not disclose potential limitations like whether the numbers are approximate, cached, or how recent the data is. For a read-only stats tool, this is acceptable 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, well-structured sentence that front-loads the tool's purpose and lists all metrics in a compact list. It avoids filler and each phrase adds meaningful content. It could be slightly shorter by dropping the 'Facts only' clause, but that clause provides a behavioral note, so it 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?

Given there is no output schema, the description must convey what the response looks like. It enumerates the categories of data but not the exact structure (e.g., field names, whether it's a flat object or nested, types). For a stats tool with zero parameters, this is a notable gap because the agent cannot predict the response format precisely. It is sufficient for basic understanding but not complete for reliable invocation without additional assumptions.

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, and the schema reflects this with an empty properties object. Per the rubric, a zero-parameter tool gets a baseline of 4 because there is nothing for the description to clarify about parameters. The description adds no param-related info, but that is not needed.

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 opens with a specific verb and resource: 'Shape of Arc's ERC-8004 agent registry in one call,' and enumerates the exact metrics returned (total ids, distinct owners, distinct hosts, resolution counts, x402 vs payment declarations, status counts, concentration shares). This clearly distinguishes it from sibling tools like arc_agents_list or arc_agent_get, which return individual records rather than aggregate statistics.

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 is for obtaining aggregate registry statistics in a single call, but it never explicitly contrasts with siblings or states when NOT to use it. For example, it doesn't say 'for per-agent details, use arc_agent_get' or 'for list view, use arc_agents_list.' The context signals make it evident it's a stats tool, but the description leaves the routing 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 provided, the description carries the burden of behavioral disclosure. It explains the call is a liveness check, mentions the §3.5 envelope return format, and clarifies that it reveals live routes. It does not discuss error behavior, but for a zero-parameter health probe this is sufficient.

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 tight, front-loaded sentences convey outcome, return style, and usage order without wasted words. 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?

Given the tool's low complexity, zero parameters, and lack of output schema, the description fully equips an agent to call it correctly: what it does, what it returns, and when to call it are all stated.

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 and schema coverage is 100%, so there are no parameter semantics for the description to add. Per the baseline for a zero-parameter tool, a 4 is appropriate; nothing is 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 clearly states the tool reports liveness of the Arc Data API and lists served routes. It uses a specific verb/resource pairing and is easily distinguished from the data-focused sibling tools like arc_agents_list or arc_token_screen.

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 explicitly instructs the agent to call this tool first, with the concrete goals of confirming the API base and seeing which routes are wired. This is actionable placement guidance even though no alternative health-check sibling exists.

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 provided, the description carries the full burden of behavioral disclosure. It explicitly warns about NO_DATA until an hourly reading exists and states that partial windows yield NO_DATA rather than false zeros—an important data-availability caveat. It does not mention read-only semantics, but the nature of the analytics tool implies it. This adds meaningful context beyond a bare statement.

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 ('Launchpad concentration on Arc over the recent window') followed by a compact list of metrics and the critical NO_DATA caveat. Every clause earns its place; no fluff or redundancy.

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 zero-parameter tool with no output schema, the description covers what it returns and the key data-availability behavior. It does not mention update frequency, units, or how to interpret HHI thresholds, but those are not strictly required for correct invocation. The NO_DATA note addresses the most common pitfall. Overall it is complete enough for an agent to call it correctly.

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 the schema is trivially covered. The description doesn't need to explain parameters, and the baseline of 4 for parameter-less tools applies. It correctly avoids inventing unnecessary parameter detail.

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 function: it reports launchpad concentration metrics (HHI, pools created, v3/v4 counts, deployer callers, per-launchpad stats) for Arc over a recent window. The verb 'concentration' and the explicit metric list make the purpose unambiguous, though it does not explicitly contrast with sibling tools like arc_health or arc_lp_apr.

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?

There is no guidance on when to use this tool versus alternatives. The description only explains what it returns and the NO_DATA condition, not the scenarios where this tool is preferred or avoided. An agent must infer its purpose from the metric list without knowing when to choose it over siblings.

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 provided, the description carries the full burden. It discloses the key assumption (price stayed in range) and the NO_DATA fallback when no scan exists, which are important behavioral details beyond the schema. It does not mention side effects or auth, but as a read-oriented query tool, these are less critical.

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 concise sentences with no filler. The purpose is front-loaded, filters are briefly listed, and key caveats are stated efficiently.

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?

The description covers the key assumption and the NO_DATA case, but it does not specify the normal return format or structure (e.g., whether it returns a single number, a list, or a table). With no output schema, this omission leaves the agent to guess the response shape, which is a notable gap for a query 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 each parameter already documented (e.g., 'Filter by pair, case-insensitive, e.g. usdc/weth'). The main description repeats these examples without adding new meaning, so it does not exceed the baseline for fully-covered parameters.

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 computes realised range-APR for Arc LP pools from the latest scan, naming the resource and output. It lists optional filters and distinguishes itself from sibling tools (which cover health, launchpads, token screening, etc.) by its specific subject matter.

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—'use this when you need range-APR'—but there is no explicit guidance on when to prefer this over alternatives or when not to use it. No sibling is named or contrasted, and the description only hints at context via 'latest scan' and 'NO_DATA' conditions.

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 behavioral burden. It discloses the verdict classification, that it explains the refusal reason, and the NO_DATA sentinel for unknown poolIds. It does not explicitly state that the call is read-only, but the informational nature of a 'verdict' makes that reasonably clear and no contradiction exists.

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 with no filler. The core purpose is front-loaded, followed by the refusal-reason behavior and the NO_DATA edge case. 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?

With no output schema or annotations, the description must cover output semantics itself. It names the verdict, the two possible classifications, the refusal-reason explanation, and the unknown-poolId sentinel. An explicit return shape would be nice, but for a single-parameter lookup tool this is enough for correct selection and invocation.

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 poolId parameter is already well-described in the input schema as a bytes32 hex string. The description merely refers to 'specific v4 poolId' without adding format, constraints, or further parameter semantics beyond the schema, so the baseline score of 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 states a specific verb and resource: it returns a 'Decoy-pool verdict for a specific v4 poolId' and defines the two possible outcomes (real venue vs high-fee decoy). This is distinct from the sibling tools, which focus on health, launchpads, LP APR, token screening, and agents, so an agent can tell this tool apart immediately.

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 clear context: use this tool for a specific v4 poolId to decide whether the pool is a decoy or the real venue, and it notes the NO_DATA case for unknown poolIds. It does not explicitly name sibling alternatives or exclusion conditions, but the unique decoy-check purpose makes the intended usage clear.

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 provided, the description carries the full burden. It discloses the output (consensus count and head) and the REFUSED status condition, which is critical behavioral context. It does not mention whether the tool is read-only, but that is implied by the nature of a consensus check. It also doesn't discuss potential rate limits or error cases, but for a simple read-only tool this is adequate.

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, both dense with information. The primary output is front-loaded, and the usage guideline is immediately actionable. No filler 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?

For a parameterless read-only tool with no output schema, the description fully explains what the tool returns and how to interpret it. It even provides a practical rule (REFUSED below 2). An agent can invoke it without further clarification.

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 there is nothing for the description to clarify. The baseline for zero-parameter tools is 4, and the description doesn't need to add parameter details. It appropriately focuses on output semantics 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's function: reporting how many of four public RPCs agreed and the agreed head. The verb 'agree' and specific resource 'Arc's four public RPCs' make the purpose unambiguous. It is distinct from sibling tools which focus on health, launchpads, APRs, token screens, etc., so there's no confusion.

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 states when to use: 'A cheap trust gate before acting on other Arc data.' It also gives a conditional threshold ('Below 2 the status is REFUSED') and instructs to treat Arc figures as unchecked until consensus is restored. This is clear, actionable guidance for an agent deciding whether to use this 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 provided, the description carries the full transparency burden. It discloses key behavioral traits: the tool is a cheap non-executing gate, tokens are refused under specific decoy-pool conditions, and NO_DATA is returned when the token has not traded in the discovery window. This is strong behavioral disclosure for a read-like screening 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?

The description is compact and front-loaded: the first sentence states the purpose and core outputs, the second clarifies scope with a critical exclusion, and the third explains the NO_DATA edge case. Every sentence earns its place 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?

For a single-parameter screening tool with no annotations and no output schema, the description gives enough to invoke it correctly: expected inputs, outputs, refusal conditions, and the no-data edge case. It does not specify the exact shape or types of the returned fields, but that is not necessary for calling the tool successfully.

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 already fully documents the single parameter 'ca' with 100% coverage, so the description adds little parameter-level meaning beyond referring to 'contract address'. The baseline of 3 applies because the schema does the heavy lifting and no additional parameter context is needed.

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 verb ('Screen'), a clear resource ('launched Arc token by contract address'), and enumerates the returned information (USDC-paired pool, fee, recent swap count, decoy-pool verdict). It also differentiates itself from siblings by explicitly noting it does NOT run a live buy/sell, which separates it from tools like arc_token_sellsim.

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 clear context for when to use the tool: as a 'cheap gate' before doing heavier checks, and it explicitly warns that no live buy/sell is executed. It does not name alternative tools or state explicit when-not-to-use conditions, so it falls just short of full 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 burden of behavioral disclosure. It explains that the tool performs a live simulation against current chain state, reports a fraction, returns NO_DATA when simulation fails, and never scores zero on a failed simulation — a useful edge-case guarantee. The paid-tier warning also adds practical context.

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 sentences with the core method front-loaded, followed by the interpretation threshold and the cost/failure caveats. Every sentence adds necessary information, and the parenthetical about failed simulations is valuable rather than 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?

For a one-parameter tool with no output schema, the description covers the operation, the result semantics, how to interpret the result, and the failure case. An agent has enough information to decide when to call it and to interpret either a numeric fraction or NO_DATA correctly.

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 schema already documents the single parameter ca with 100% coverage, so the baseline is 3. The description adds no extra parameter-level guidance, but none is needed for a single well-documented contract-address parameter.

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 opens with a specific verb and resource: a honeypot test for an Arc token via a live buy-then-sell simulation. It also states the output — the round-trip fraction recovered — which clearly separates it from siblings like arc_token_screen or arc_pool_decoy even without naming them.

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 decision threshold: below ~0.9 the token is likely a honeypot or punitive-tax trap. It also flags the route as heavy and paid-tier, warning the agent about cost. However, it does not explicitly name alternative tools or state when NOT to use this tool, so it stops short of a 5.

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