SaltCrate Oracle

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

With no annotations, the description carries the burden and does disclose useful behavior: it is stateful (compares against the last check) and it enumerates the possible outcomes ('new', 'changed', 'unchanged') including the first-call special case. It does not mention any auth, rate-limit, or persistence-store caveats, which keeps it short of a 5.

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 user-facing question before the implementation detail. Every sentence carries information and 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?

For a one-parameter tool with no output schema, the description covers what the agent most needs to know: statefulness and the set of possible return values. Missing are edge behaviors such as what happens on fetch failure or how state is scoped, which keeps it below 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 0%, so the description ideally would compensate for the single url parameter, but it adds no explicit detail about the parameter (format, expected scheme, whether redirects are followed). The url name is largely self-evident, so this is adequate but not additive.

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: checking whether a web page changed since the last check, with the mechanism (hash-based) named. It partially differentiates from siblings by emphasizing change detection rather than fetching or link validity, though it never explicitly names check_link/fetch/verify.

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 — monitoring a page over time — but there is no explicit when-to-use versus when-not, and no sibling alternatives are named even though check_link, fetch, and verify all touch the same web resources. The agent must infer that this is the stateful change tracker.

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

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the return payload (HTTP status, redirect chain, final URL, latency) but says nothing about side effects, timeouts, rate limits, redirect handling, or authentication needs.

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 sentences, zero waste, with the core purpose front-loaded and the return details following immediately.

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 does a good job enumerating what comes back (status, redirect chain, final URL, latency). Only behavioral caveats like timeouts or request semantics are missing for a network-probing 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 0% for the single url parameter, so the description should compensate, but it only implies that a URL is the input. The parameter is largely self-explanatory from its name, so the gap is minor.

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+resource (check whether a URL is live) and names the diagnostics returned, so the tool's job is unmistakable. It doesn't explicitly differentiate itself from siblings like fetch or verify, which is the only gap.

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 rhetorical question 'Is this URL live right now?' implies the use case (connectivity/liveness troubleshooting), but there is no explicit when-to-use, when-not-to-use, or reference to the sibling alternatives fetch, verify, or check_change.

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

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

With no annotations, the description carries the full burden and does well: it discloses the content-cleaning transformation and the exact return payload (text, title, content-type, HTTP status, length). It omits auth requirements, rate limits, timeouts, JS-rendering behavior, and error handling, so it stops short of exhaustive disclosure.

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, zero waste, with the core capability front-loaded ahead of the return-value detail. Every clause 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?

No output schema exists, but the description compensates by enumerating return fields, and it covers the transformation behavior in the absence of annotations. For a one-parameter tool this is nearly complete; only failure/timeout behavior is unaddressed.

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 0% and there is a single url parameter. The description implies the parameter is a web page URL, which gives basic meaning, but adds no format, scheme, or constraint details beyond the obvious. Marginal value over the bare 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 names a specific verb (get/extract) and resource (text from a web page), and specifies the scope of extraction: boilerplate, navigation, and ads stripped. An agent can distinguish this retrieval tool from check_link/verify/check_change, which are checking tools, 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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives. A phrase like 'so you can work with the actual content' implies a reading use case, but nothing tells the agent when to call fetch versus check_link or verify.

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 usefully discloses the return shape (confidence score, matched terms, best excerpt) and, importantly, the underlying method (heuristic term-overlap, not semantic fact-checking), setting honest expectations. It does not disclose failure modes, error behavior, or 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?

Two tightly written sentences: the question first, then the return description and the crucial caveat. Every clause 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 two-param verification tool without an output schema, the description covers purpose, return fields, and the heuristic caveat. It stops short of preconditions (URL must be fetchable) and error behavior, leaving minor 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?

Schema coverage is 0%, so the two parameters (claim, source_url) are only named, not described. The description implies the argument shapes through its question but adds no format, length, or URL-validation detail. Baseline is low-context but the current text does not compensate for the coverage gap.

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 question the tool answers ('Does this source URL support a given claim?') and names the resource (source URL, claim). Distinguishable from siblings like fetch, check_link, check_change, which do not perform claim verification.

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 clarifies the tool is heuristic term-overlap rather than semantic fact-checking, which implicitly guides against fact-check use. However, it never states when to use this tool versus fetching the URL directly or using the other sibling tools.

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