LLM Red-Team Scanner

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

With no annotations, the description carries the full burden; the 'get_' prefix and 'info' wording suggest a read, and it usefully discloses the actual price (0.15 XNO) and accepted payment rails (ERC-20, Lightning, card). It does not say whether the price is one-time or recurring, whether it is cached, or what the response contains, which matters for an unannotated 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?

One compact line with the key information (what it is, price, payment methods) front-loaded. The slash-delimited feature list costs a little density but no sentence is wasted.

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 pricing lookup with no annotations and no output schema, the description should at minimum clarify tier scope (one-time vs subscription) and whether payment happens here or via get_purchase_flow; it gives price and rails but leaves that routing ambiguous.

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 takes zero parameters, so there is nothing for the description to disambiguate; the baseline 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?

The description opens with a specific resource label, 'PRO pricing & payment info', which tells an agent this tool returns the paid tier's cost and payment details, separable from get_purchase_flow and run_free_scan. The remainder is a feature list that muddies rather than sharpens the 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?

Usage is only implied: an agent can infer you call this to learn PRO cost, but there is no explicit when-to-use, no mention of get_purchase_flow as the follow-up, and no statement that this is informational only and does not initiate a transaction.

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 disclosure burden and does a strong job: it names accepted payment methods and amounts (0.15 XNO or USDC on Base via x402), states that no human is in the loop, and describes callback push plus poll fallback delivery. It leaves some ambiguity about whether calling the tool is purely read-only or can initiate payment, and does not mention auth or rate-limit 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 front-loaded sentence that states the tool's purpose immediately and then packs in payment and delivery details without obvious filler. Every clause contributes useful context for an agent deciding what this tool is for.

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 a zero-parameter tool with no annotations and no output schema, the description supplies the core conceptual context: payment options, no-human-loop execution, and delivery via callback or polling. It still does not specify the return format or explicitly clarify whether the response is a procedure document versus an executed purchase, which leaves a minor completeness gap.

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 under the scoring rules. The description does not need to document parameter meaning, and no meaningful parameter 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 frames the tool as a machine-readable autonomous purchase procedure, including payment methods and PRO download delivery. It is specific enough to distinguish it from get_pricing and run_free_scan, but it does not explicitly name those siblings or use a direct verb like 'returns' to eliminate all ambiguity about whether it returns instructions or performs a purchase.

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 this is used when an agent needs to autonomously purchase PRO access, but it gives no explicit when-to-use or when-not-to-use guidance. It also does not mention get_pricing as the alternative for retrieving price information, or clarify prerequisites such as whether a free scan is required first.

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 fully disclose behavioral traits. It states the polling behavior and the done condition, but does not describe error handling, timeouts, whether it blocks, or the response structure. The agent is left without information about failure modes or what 'done' actually returns.

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 entire description is a single front-loaded sentence with no redundant words. It states the action, the input source, and the termination condition efficiently, earning its place with no fluff.

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 that presumably returns scan results, the description does not explain what the response contains, what statuses exist beyond 'done', or how failures are indicated. Since there is no output schema, this is a significant gap that could lead an agent to mishandle the result.

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 provides only the type (string) for job_id with zero description coverage. The description adds critical context that the job_id originates from run_free_scan, which tells the agent where to obtain it. This meaningfully compensates for the schema's lack of documentation.

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 'poll' and the resource 'a scan by job id', and it explicitly ties the job id to the output of run_free_scan, which distinguishes it from siblings. It also defines the termination condition ('until status=done'), making the tool's purpose unambiguous.

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 correct usage context by noting the job id is returned by run_free_scan, indicating this tool should be used after initiating a scan. It does not explicitly mention when not to use it or alternatives, but the flow is clear enough for an agent to select it appropriately.

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 disclosure burden and does well: it reports the ~35s runtime, that the spec is sent through live adversarial probes, the two-part execution model, and what is returned. It stops short of disclosing limits an agent would want — rate limits or quotas on 'free' scans, whether the spec is retained, and what happens on probe failure.

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?

Three tight sentences, front-loaded with the value proposition and duration, then the mechanism, then the return payload. Every clause carries information; nothing is padded.

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, and the description compensates by naming the return contents — 0-100 risk score, per-finding evidence, and guardrail sentences per gap. Combined with a single fully documented parameter, an agent has everything needed to call and interpret this 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% with a single parameter already documented as 'Your agent / system prompt (>=20 chars)', so the baseline is 3. The description adds no further detail about the spec format (e.g., whether it accepts multi-message transcripts or only a single prompt string), so it does not improve on the schema.

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 and resource — a free LLM agent security review — and then enumerates exactly what it does: 8 live adversarial probes plus a deterministic static audit of the spec. An agent can distinguish this from siblings like get_scan_result (which fetches results) or get_pricing without opening a schema.

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 'Free' and by the input being an agent spec, so the context of use is reasonably clear. However, it never states when to prefer this over a paid/other scan, what happens if results are needed later (i.e., that get_scan_result exists for retrieval), or any prerequisites such as spec length beyond the schema's minimum.

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