agentweb

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

With no annotations provided, the description carries full responsibility for disclosing behavioral traits. It accurately describes the tool's output (read-only metadata retrieval) and implies non-mutating behavior through the verb 'return.' It doesn't mention latency, potential errors, or prerequisites, but for a simple provenance check this is reasonable. The phrase 'primary-source verified' adds useful context about data quality semantics beyond a mere return type.

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 essential. The first sentence lists the exact data points returned, and the second provides actionable usage context. There is no fluff, redundancy, or unnecessary elaboration—every word 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 tool with no parameters and no output schema, the description must clarify what the tool returns and when to use it. It fully covers this: it names the four types of information returned (source, date, coverage, confidence) and explains the purpose (checking data currency and field verification). Given the tool's simplicity and the absence of sibling overlap, this is 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 tool has zero parameters, and the schema confirms this (with 100% coverage). The description correctly avoids inventing parameter details, which aligns with the baseline for no-parameter tools. No semantic enhancement is needed beyond what the schema already conveys.

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 returns specific dataset metadata (source, as-of date, coverage counts, per-field confidence) using a specific verb ('Return'). This unambiguously distinguishes it from sibling tools (list_jurisdictions, lookup_jurisdiction) which focus on jurisdictional data rather than dataset provenance.

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 explicit usage guidance: 'Call this before relying on any answer, to check how current the underlying data is and which fields are primary-source verified.' This directly tells the agent when to invoke this tool and what to evaluate, effectively guiding tool selection. While it doesn't name alternatives, the context makes the distinction clear enough.

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 (readOnly, destructive, etc.), the description carries the full burden. It does not disclose side effects, whether the operation is read-only, authentication requirements, or rate limits. As a listing tool, it is implicitly read-only, but this is not stated, leaving behavioral transparency lacking.

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, concise and well-structured. It provides the core purpose and immediately explains the key parameter's values without fluff, making it efficient and readable.

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 is complete for a simple listing tool: it explains the purpose, parameter usage, and even default behavior (omit for all). It does not describe the output format, but no output schema is provided, and for a list operation this is acceptable. It could mention sorting or pagination, but these are not critical, so it earns a 4.

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 describes each parameter, but the description adds significant nuance for the posture parameter by explaining the meaning of each enum value (e.g., 'adopted_model_bulletin = adopted the NAIC bulletin'). This enriches the schema, though since and until are already clear. Coverage is high, and the added value justifies a score above the baseline.

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: 'List US jurisdictions by regulatory posture.' It specifies the verb (List), the resource (US jurisdictions), and the scope (by regulatory posture). It distinguishes from sibling tools by implying a list operation versus lookup or provenance.

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 usage guidance for the posture parameter (e.g., 'Use posture ... for states that adopted...'), but it does not explicitly contrast with sibling tools like lookup_jurisdiction or dataset_provenance. It lacks explicit when-to-use versus alternatives, so it is only somewhat useful.

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 transparency burden. It includes a behavioral caveat: 'Note: not adopting the bulletin does NOT mean a state is unregulated — check other_activity in the response.' This clarifies interpretation of results. However, it does not explicitly state whether the operation is read-only or has side effects, though a lookup implies safety.

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 concise, using two sentences plus a brief note. It front-loads the purpose, lists specific data points returned, and adds a crucial caveat in a clear separate sentence. No redundant or vague wording.

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 (single parameter, no output schema), the description fully covers what the tool does, what it returns (citations, dates, status), and includes an important interpretive note. It is complete for a lookup tool without needing an output schema.

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 fully describes the parameter (two-letter code or full name, e.g., 'CO' or 'Colorado'), so coverage is 100%. The description adds only that it is a 'US jurisdiction,' which is implicit from the schema's state code example. It does not provide additional semantic details beyond the schema, so 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 clearly states the tool's function: 'Look up one US jurisdiction's insurance-AI regulatory posture' and enumerates specific aspects (adopted NAIC model bulletin, own framework, other legislation). It distinguishes from sibling tools like list_jurisdictions (which likely enumerates) and dataset_provenance (which likely provides source metadata).

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 explicitly specifies when to use the tool: 'Call this when asked what a specific state requires, whether a state adopted the NAIC AI model bulletin, or what AI insurance legislation a state has.' This provides clear, actionable conditions and implies it is not for listing all jurisdictions.

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