Xingchen SentriScan ASP

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 does state what risk categories are checked, which gives useful insight into the tool's behavior. However, it does not disclose whether the audit is static or dynamic, whether it is read-only, what it returns, or any side effects, leaving important behavioral gaps.

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, focused sentence with parenthetical specifics. It is concise, front-loaded with the core purpose, and every part contributes meaning. There is no redundant or filler content.

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 absence of annotations, an output schema, and meaningful parameter metadata, the description is too thin for confident invocation. It does not explain where the Solidity contract comes from, what the audit output looks like, how results are interpreted, or any limitations. The tool name and description provide orientation but not enough operational context.

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 no parameter documentation burden. The input schema is an empty object and schema description coverage is 100%, so the description does not need to explain parameters. A baseline score of 4 is appropriate for this parameter-free tool.

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 a specific action ('audit') and resource ('Solidity'), and enumerates concrete risk categories it covers: honeypots, selfdestruct, and delegatecall. This is more specific than a tautology and helps differentiate it somewhat from general scanning siblings, though it does not explicitly name an alternative.

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 phrase 'pre-flight' implies the tool should be used before deployment or interaction with a Solidity contract, giving some contextual guidance. However, there is no explicit statement of when to use this tool versus alternatives like scan_code_secrets or validate_evm_address, and no exclusions or prerequisites are provided.

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 conveys the core calculation but omits other behavioral aspects. It does not state whether the tool is read-only, what side effects (if any) occur, or how it interacts with the environment. Without annotations, this minimal transparency is insufficient.

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, concise sentence that effectively conveys the purpose without unnecessary detail.

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 lacks critical context: it does not describe the output format, any edge cases, or how the tool fits into a larger workflow. Given the absence of an output schema and annotations, this brevity leaves the tool under-specified for practical use.

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 shows no parameters, and the description provides no information about expected inputs or how any inputs affect the calculation. It mentions factors like gas and fees but does not clarify if these are passed as parameters or assumed from context, leaving parameter semantics completely unspecified.

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 action (calculates) and resource (net arbitrage profit), including specific factors (gas and fees). However, it does not explicitly differentiate from sibling tools like calc_impermanent_loss, though the name and function are distinct enough for basic identification.

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 usage guidance is provided. The description does not indicate when to use this tool, any prerequisites, nor any conditions under which to prefer it over 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?

No annotations are provided, so the description carries the full burden of disclosing behavior. It states that the tool computes something, but it does not describe the output form at, assumptions, or what 'exact' means operationally. For a tool with no output schema, this is insufficient behavioral transparency.

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 one concise sentence with no filler. Every word contributes to the core purpose, and the key subject matter 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?

Because there is no output schema, the description must explain enough for an agent to use the result correctly. It only gives the abstract computation and audience, leaving ambiguity about what 'IL vs Fee APR' output looks like and whether any hidden inputs or assumptions are involved.

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 input parameters, so there is nothing for the description to add beyond the schema. Per the rubric, zero parameters baseline is 4.

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 ('Computes') and a clear resource ('exact IL vs Fee APR for liquidity providers'). It is easily distinguished from sibling calculation tools like calc_arbitrage_spread because the subject matter is unique.

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 phrase 'for liquidity providers' gives implied usage context, but the description does not explicitly state when to choose this tool over alternatives or mention any exclusions. There is no direct comparison with sibling tools.

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 burden. It mentions 'heuristic repair' (a behavioral trait) but does not disclose limitations, error handling, side effects, or what constitutes 'dirty' JSON. The heuristic nature could imply non-deterministic results, but this is not elaborated.

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 concise sentence with no redundant words. It efficiently conveys the core purpose without unnecessary elaboration.

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 is present, so the description should explain what the tool returns or how the repair result is communicated. It does not mention return type, success/failure indicators, or any side effects. The description is too brief for an agent to fully understand the tool's contract, especially given the ambiguity about input.

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 has no parameters (empty object), but the description does not clarify what input the tool expects. It mentions truncated or markdown-wrapped JSON, implying a JSON input, but the lack of parameters leaves ambiguity about how the input is provided. With zero parameters, the description should still specify the tool's operational context, which it fails to do.

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 'repair' and resource 'JSON', with concrete conditions (truncated or markdown-wrapped). It clearly distinguishes the tool's purpose, though it could be slightly more explicit about the exact transformation (e.g., 'clean' vs 'repair').

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 on when to use this tool versus alternatives. Sibling tools like extract_clean_markdown suggest overlapping functionality, but the description does not clarify when this should be preferred. Lacks explicit conditions or exclusions.

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 states the core detection behavior but does not clarify whether 'flags' means returning results, writing output, or requiring prior transaction data. Side effects, permissions, and return format are all undisclosed.

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, focused sentence with no wasted words. Every term contributes to meaning, and it is fully 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?

For a zero-parameter tool, the description conveys the essential function, but it omits the output shape, when to choose this over siblings, and any behavioral caveats. It is adequate for a basic understanding but leaves gaps for confident 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?

The tool accepts zero parameters, so there is no parameter burden for the description to carry. The baseline of 4 applies because no parameter semantics need to be explained.

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 ('Flags') and names a precise artifact ('circular transaction patterns across wallets'). It clearly communicates what the tool does and distinguishes it from unrelated siblings like assess_contract_risk or calc_arbitrage_spread.

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 on when to use this tool versus alternatives, nor any preconditions or context for invoking it. The agent must infer usage entirely from the tool name and one-line description.

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 disclosure burden. It discloses the main effect of stripping HTML and a quantitative benefit of up to 80% token savings, which is useful. However, it does not describe the return value, whether the operation is lossy, or any edge behaviors or limitations.

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, efficient sentence with no filler and the key benefit front-loaded. It could be more specific about Markdown output, but it is appropriately concise for a simple tool.

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, no-output-schema tool, the description is mostly sufficient, but it omits an explicit statement that the tool returns clean Markdown and does not clarify what input it acts on, such as a provided HTML string versus fetched content.

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 baseline is 4. The description adds a little context by naming HTML as the target, but there is no parameter-specific information to add.

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 verb 'Strips' with object 'bloated HTML' communicates a clear transformation, and the tool name extract_clean_markdown identifies the output format. It is distinct from sibling tools like clean_dirty_json, which target JSON. However, the description itself never explicitly says the output is Markdown, relying on the name.

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 phrasing implies the tool is for HTML that contains bloat and should be used when token reduction for LLMs is desired. But there is no explicit when-to-use/when-not-to-use statement, no prerequisites, and no comparison to alternatives such as clean_dirty_json or format_market_factors.

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 behavioral disclosure burden. It does add a useful trait—deterministic—implying repeatable output and no external randomness. However, it does not disclose whether the tool returns raw numbers, formatted output, or errors on malformed inputs, and the name/description mismatch ('format' vs 'calculator') is left unresolved.

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, front-loaded sentence with no filler or redundant phrasing. Every word contributes meaning, making it easy to scan.

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 the input side is complete, but the description omits what the output looks like and leaves acronyms and domain terms undefined. An agent can infer that a factor calculation occurs, but not the format or semantics of the result, making this minimally viable rather than complete.

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 is an empty object with zero parameters, so there are no parameter semantics to document. The baseline for a zero-parameter tool is 4, and the description does not need to compensate for missing parameter details.

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 calculation domain—MA, bias, and momentum factors—and notes deterministic behavior, so the tool's purpose is fairly clear. However, it never expands 'MA' and uses 'calculator' rather than matching the 'format' verb in the tool name. It also does not explicitly differentiate this from the sibling market/risk calculation tools.

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 the sibling calculators such as calc_arbitrage_spread or detect_wash_trade_flow. There is no mention of intended data types, prerequisites, or contexts that would help an agent choose 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?

No annotations are provided, so the description must carry the full behavioral burden. It only says the tool calculates fees, without disclosing whether it is pure computation, whether it depends on network state, whether it has side effects, or what assumptions it makes about urgency.

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 concise sentence with no filler, which is structurally strong. However, the phrase 'by urgency' is vague and under-specified, so the sentence does not fully earn its place by communicating enough to guide correct invocation.

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 annotations, no output schema, and no parameter schema, the description is too minimal to be complete. It fails to explain the meaning or format of urgency, which blockchain network or fee units are involved, or what the returned MaxFee and PriorityFee values represent.

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 has zero parameters, yet the description says fees are calculated 'by urgency.' This creates ambiguity about how urgency is supplied, whether via context, hidden inputs, or an undocumented parameter. With 0 params, the description should explicitly clarify the absence of arguments, but it does not.

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, 'Calculates', and identifies the resource and results: optimal MaxFee and PriorityFee. It is distinguishable from the listed sibling tools, though it does not explicitly differentiate itself from 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?

No guidance is provided about when to use this tool versus alternatives or what conditions make it the right choice. The sibling list includes other calculation tools, but the description offers no routing hints.

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 burden. It states what it detects (high-entropy API keys, private keys, tokens) but doesn't disclose whether it modifies anything, whether it scans a repo/path/string, or what the output format is. It's a scanner, so it's likely read-only, but that's not explicitly stated.

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?

One sentence, front-loaded with the key terms, no waste. 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?

For a 0-param tool with no output schema, the description is mostly complete. However, it doesn't specify the input source (e.g., does it scan a file, a repo, a code snippet?) or the output format. An agent might not know how to invoke it without that context.

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 0 parameters, so the schema is trivial. The description adds meaning by specifying what the scanner looks for, which is the only semantic content needed. Baseline 4 for 0 params 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 ('scans') and names the resource ('code') plus the target artifacts ('API key, private key, and token leak'). It clearly distinguishes itself from the sibling tools, which are about contract risk, arbitrage, markdown, etc. It doesn't explicitly name the sibling it is not, but the resource and target are specific enough.

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 the tool is for scanning code for secrets, but it doesn't state when to use it vs alternatives or any exclusions. There are no sibling tools that do secret scanning, so the context is clear enough, but no explicit guidance is given.

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 behavioral traits are disclosed beyond the basic verification action. The description does not indicate what the tool returns, whether it has side effects, or how it behaves on valid versus invalid inputs. There are no annotations to supplement this, so the agent has no insight into the tool's runtime behavior.

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, concise sentence that front-loads the key action ('Strict verification') and directly states the target resource. There is no unnecessary verbosity or filler, making it efficient and easy to parse.

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 minimal schema, lack of annotations, and absence of output description, the tool is extremely incomplete. It does not explain what 'verification' means in terms of results, how to interpret the outcome, or what edge cases exist. The description alone is insufficient for an agent to use 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 input schema is an empty object with no properties, and the description does not clarify what input is expected. It mentions 'address' but does not explain where the address comes from, how it is passed, or what format is required. This leaves the parameter semantics completely undefined.

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 purpose: strict verification of EVM, zero, and burn addresses. It uses a specific verb ('verification') and resource ('EVM, zero, and burn addresses'), which distinguishes it from the unrelated sibling tools. However, the term 'strict' is vague and could be more explicit about what verification entails (e.g., checksum validity, format).

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 no guidance on when to use this tool versus alternatives, or under what conditions it should be invoked. It does not mention any prerequisites, limitations, or typical use cases, leaving the agent without direction on when to select it.

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