Verbaterm Policy Intelligence

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

No annotations are provided, so the description carries full burden. It discloses that the tool debits an allowance and requires an API key, implying mutability. However, it does not cover error behavior, rate limits, or side effects beyond allowance deduction, leaving 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, well-structured sentence that front-loads the core purpose and immediately follows with key constraints, making it highly concise and efficient.

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 complexity of a nested object parameter and no output schema, the description is marginally adequate. It explains the basic function and a key behavioral trait (allowance debit), but does not clarify the meaning of 'citation-grounded' or the two kinds of reviewRef, which could confuse the agent.

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%, so baseline is 3. The description adds no extra meaning beyond the schema; it does not explain the structure of 'reviewRef' or the meaning of 'citation-grounded' in relation to parameters.

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 ('Ask') and the resource ('a citation-grounded follow-up question about a public library review or a private session'), distinguishing it from sibling tools which focus on retrieving reviews or listing policies.

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 mentions prerequisites (Verbaterm API key) and cost (debits Q&A allowance), but does not explicitly state when to use this tool over alternatives, nor does it clarify that it is intended as a follow-up to an existing review or session.

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?

Without annotations, the description carries the burden. It discloses that the tool returns a judged review with specific elements and instructs to cite source URLs. However, it does not mention error handling, authentication requirements, or side effects beyond reading.

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 long, front-loading the core contents and adding a practical instruction. It is efficient and each sentence adds value.

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 lack of an output schema, the description provides some structure (findings, scores, summary, provenance) but does not elaborate on return format or error cases. The sibling context suggests related tools but no missing details.

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 low (33%), and the description does not explain the meaning of any parameter except indirectly via context. The parameter semantics are left unexplained, requiring the agent to infer from names and schema descriptions alone.

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 retrieves a full judged review for a single published policy, listing specific components like findings, citation excerpts, scores, summary, and provenance. This distinguishes it from sibling tools such as get_private_review_result.

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 does not provide guidance on when to use this tool vs. alternatives, such as when a private review is needed. No explicit context or exclusions are 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?

With no annotations provided, the description must convey behavior. It implies a read operation ('poll'), but does not disclose idempotency, response format, or whether multiple polls are safe. The bare description leaves room for interpretation.

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 purpose. Every word is necessary; there is no extraneous information.

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 low complexity (1 parameter, no output schema), the description adequately covers purpose and usage context. However, it does not explain the nature of progress (e.g., percentage, status) or the response structure, which would be useful for a polling 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?

The single parameter sessionId is not described in the schema (0% coverage). The description's context ties sessionId to the output of start_private_review, adding meaning beyond the raw schema. However, it does not specify the format or source of sessionId.

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 polls progress of a private review, using the specific verb 'poll' and resource 'progress of a private review'. It distinguishes itself from siblings like start_private_review and get_private_review_result by tying it explicitly to a prior action.

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 indicates this tool should be used after start_private_review, providing clear context. However, it does not explicitly state when not to use it or mention alternative tools like get_private_review_result for completed reviews.

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 full burden. It discloses that raw source text is not returned, which is a key behavioral trait. However, it does not confirm idempotency, safety, or whether it requires the session to be completed (implied but not explicit).

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 sentence with 15 words, front-loading the purpose and essential constraint. No unnecessary 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?

For a single-parameter, no-output-schema tool, the description covers the return content (findings+citations), what is excluded (raw text), and the prerequisite (session started). It could mention error conditions but is adequate overall.

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% but the description effectively explains that sessionId refers to the session started by start_private_review, providing context beyond the schema's type-only definition. Single parameter clarity is high.

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 retrieves completed private review results (findings and citations) for a specific session. It distinguishes from siblings like start_private_review and get_private_review_progress by specifying it gets the final result, not starting or checking progress.

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 session must have been started via start_private_review, but does not explicitly state when to use this tool versus alternatives like get_private_review_progress (for status) or ask_question (for queries). No exclusions or prerequisites are listed.

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 provided, and the description adds no behavioral details such as pagination, sorting, rate limits, or any side effects. It is a bare minimum statement.

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?

A single sentence that is front-loaded with the verb 'List' and the object. Every word is necessary; no redundancy.

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 should explain return values or structure. It does not. Also lacks context on ordering or filtering. Minimal completeness given the tool's simplicity.

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 has zero parameters, so baseline is 4 per rules. Description adds no parameter information because none exist.

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 'list' and resource 'published public-library policy reviews'. It distinguishes from siblings like 'search_policies' by specifying 'published' and 'public-library', making its scope 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?

No guidance on when to use this tool versus alternatives. For instance, no mention of scenarios where 'search_policies' might be preferred. Description merely states what it does without usage context.

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 fully bears the burden of behavioral disclosure. It clearly states that the tool returns 'derived review metadata — findings counts, scores, freshness — never raw policy text', which is a critical behavioral trait. It does not cover authentication or rate limits, but for a search tool, the key behavior is well-described.

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, well-structured sentence that efficiently conveys the tool's purpose, scope, and return type. Every word adds value, and it is front-loaded with the most important information.

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 low complexity (3 simple parameters, no output schema), the description provides sufficient context about the corpus type and return value. It does not detail search semantics (e.g., fuzzy matching), but the schema descriptions partially cover that. Overall, it is adequate for agent 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?

Schema description coverage is 100%, so the baseline is 3. The description does not add any new meaning beyond what the schema already provides for the three parameters (q, limit, category). It rephrases but does not enhance understanding.

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 'Search', the resource 'Verbaterm's judged, citation-checked public policy corpus', and the scope 'companies, products, policy kinds'. It also specifies what it returns (derived review metadata) and what it does not (raw policy text), making it distinct from siblings like list_policies.

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 when to use this tool (searching for derived metadata) and when not (for raw text), but does not explicitly list alternative tools or conditions. It provides clear context for the tool's purpose, but lacks formal exclusion statements.

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?

Discloses key behavioral traits: requires API key, consumes plan allowance, returns sessionId for polling. However, no annotations are provided, so the description carries full burden. It lacks details on idempotency, error states, or side effects beyond allowance debit.

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 concise sentences: first sentence states the action and key conditions, second sentence explains the return value. No unnecessary words, front-loaded with critical information.

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?

Explains the return value (sessionId) and the polling workflow, which is essential since there is no output schema. Covers billing implications and requirements. However, could benefit from mentioning minimum text length (already in schema) or error handling.

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 67% (policyKind and policyText have descriptions, documentTitle does not). The tool description adds no additional parameter information beyond what the schema provides, so it meets the baseline for moderate coverage.

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?

Clearly states the action 'Start a private Verbaterm review of pasted policy text', specifying the verb (start) and resource (private review). Distinguishes from siblings by mentioning it requires polling with get_private_review_progress and that it debits plan allowance.

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?

Explicitly notes prerequisites (Verbaterm API key) and billing impact (debits plan allowance, not credits). Implies usage context as the starting point for private reviews, but does not explicitly state when not to use or provide alternatives among siblings.

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