SCRIPTMASTERLABS — SML agent-safety

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 prices and 402 terms but does not explain what '402 terms' means, whether authentication is required, how the catalog is returned, or any rate limits.

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 short phrase with no wasted words. However, it is so terse that key details are omitted rather than efficiently conveyed.

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 catalog tool with no output schema, the description gives a minimal indication of content (prices, 402 terms) but does not explain the return format or the meaning of '402 terms'. It is adequate but leaves clear gaps.

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. There is no parameter meaning to add beyond the empty 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?

The description identifies the resource as a machine-readable catalog containing prices and 402 terms, but it does not state the action (e.g., retrieve, list) or differentiate this tool from the sibling token-risk tools. The purpose is inferable but vague.

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 the token-risk alternatives, nor any mention of prerequisites or expected context. The agent must infer usage entirely.

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 only declare readOnlyHint=true, and the description usefully adds the paid-call price ($0.004 via x402), the transport (POST to a specific endpoint), and the shape of what comes back. It does not cover failure modes, payment/auth flow, or rate limits, so it adds value without fully discharging the behavioral burden.

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 compact sentences carry purpose, price, endpoint, and the return fields with no filler. The endpoint URL is long but is genuinely load-bearing information for invoking the paid service.

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, the description compensates by enumerating the result fields (verdict, score, categories, matched spans, obfuscation tricks, recommendation). It stops short of explaining error handling or what happens when payment is not prearranged, which matters for a paid remote call.

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 there is a single required parameter whose meaning is already documented as 'Agent-bound text to classify'. The description's 'POST {text}' restates the parameter without adding format, length, or content guidance.

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: a prompt-injection check that classifies agent-bound text. It is clearly distinguishable from siblings like url-safety and x402-health by subject matter, though it never explicitly contrasts itself with 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?

There is no guidance on when to run this check versus url-safety, or on preconditions such as needing an x402 payment setup. The agent must infer usage entirely from the name and the schema's 'Agent-bound text to classify' note.

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 only declare readOnlyHint=true, so the description carries real weight and delivers: it discloses the $0.004 x402 cost, the exact paid endpoint, and the shape of the result (verdict tiers plus score and reason categories). That answers the questions an agent most needs before spending money, though it omits payment-flow mechanics and any rate/availability limits.

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 dense sentence that is front-loaded with the purpose and cost, then the endpoint, then the return contract. The telegraphic fragments are efficient rather than padded, with no restated boilerplate.

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 read-only check with no output schema, the description covers what the tool does, what it costs, and what comes back including the detection categories. Remaining gaps (URL input format, payment handshake details) are minor for a tool of this complexity.

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 0%, so the bare "url" string property carries no meaning on its own; the description partly compensates with "GET ?url=", confirming a single URL query argument. It still does not state format expectations (scheme required, host-only, IDN handling) that matter for a URL-validation 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?

"URL safety check" gives a specific verb+resource, and the parenthetical endpoint reinforces that it evaluates a single URL rather than scanning content. It is distinguishable from prompt-injection (text scanning) and x402-health (service status), though it never names those siblings explicitly.

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 by the subject matter: you call it to vet a link before an agent follows it. There is no explicit when-to-use statement, no exclusion telling the agent to use prompt-injection for prompt text instead, and no note about when a paid call is warranted.

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 readOnlyHint=true annotation already covers the safety profile, and the description usefully reinforces it with 'Live probe (never pays)' while enumerating the response payload (verdict, recommended option, accepts problems, discovery/bazaar metadata, latency) – valuable because there is no output schema. However, it omits the cost implication on the target side, rate limits, and any auth requirements for the probed endpoint.

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 purpose is front-loaded and nothing is padded, but the telegraphic style – a raw query-string fragment and a run-on list of payload fields – makes it harder to parse than a plain sentence would be. The '$0.002 via x402 at <URL>' clause is essential context but competes for attention with the field list.

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 3-parameter probe with no output schema, listing the returned signals is the right move and largely discharges the return-value burden. It still doesn't resolve the two biggest ambiguities an agent faces: that 'url' is the remote endpoint being probed (not this service's own address) and what happens when the probe fails or the target is unreachable.

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 0%, so the description must carry the parameter burden. It only echoes the query string ('?url=&method=GET|POST&maxUsd='), which restates names and the method enum already present in the schema; it never explains that url is the target endpoint to probe, or what maxUsd bounds (maximum acceptable price) and how it affects the verdict.

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 the resource precisely ('x402 endpoint health / pay-readiness') and specifies the checks performed (go/caution/no_go verdict, recommended payment option, accepts problems, latency), so an agent knows what it gets back. It never states a clean verb and never contrasts itself with the sibling tools (catalog, prompt-injection, url-safety), so differentiation is by name only.

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 explicit when-to-use or when-not-to-use guidance; the intended moment (probing an x402 endpoint before paying it) is only implied by 'pay-readiness' and 'never pays'. With url-safety and catalog as siblings, the agent is left to infer that this tool is for payment-capability probing rather than general URL vetting.

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