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

With no annotations provided, the description must disclose behavioral traits. It states that the tool returns MAD and χ² and that it is not for individual judgment, but it does not explicitly mention that it is read-only or describe how it handles edge cases (e.g., zero or negative amounts). Since the name and nature imply a non-mutating analysis, the description is adequate but not rich.

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 with no filler. The core purpose and a critical usage constraint are front-loaded, and 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?

Given the tool's moderate complexity (3 params, no output schema, no annotations), the description covers the essential usage distinction and return metrics. It does not detail the exact output shape, but for a simple statistical result this is a minor gap. Overall, the description is sufficiently complete for an agent to call the tool correctly.

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% – all three parameters (digits, amounts, journals) have clear descriptions in the schema. The tool description adds little beyond the schema, but it does clarify the overall purpose, which indirectly aids parameter understanding. Baseline 3 is appropriate when schema fully documents 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 states a specific verb ('compare'), a specific resource (leading-digit distribution of amounts), and the output (MAD and χ²). It also explicitly distinguishes the tool from individual-entry judgment, which differentiates it from siblings like screen_journals and detect_duplicates.

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 clearly states when to use it (for population properties) and when not to (for individual journal judgment). It does not name an alternative tool explicitly, but the exclusion is unambiguous and sufficient for an agent to avoid misuse.

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 burden of behavioral disclosure. It clearly states this is a read-only filter that returns only unbalanced journals and frames it as a data-quality pre-filter, which is the main behavior an agent needs to know.

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 short, purposeful sentences; the core behavior is front-loaded and the second sentence adds a concrete use case. There is no filler or repetition.

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 tool is simple, accepts one well-documented parameter, and the description states both the input purpose and the output predicate. It is fully usable without needing extra edge-case or output formatting 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 description coverage is 100%, so the baseline is 3. The description adds a tool-level purpose but does not expand on the `journals` parameter semantics beyond what the schema already documents.

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 uses a specific verb ('返す') and a precise resource ('貸借が一致しない仕訳だけ' return only unmatched journal entries), clearly distinguishing this from sibling tools like screen_journals or detect_duplicates. It defines the tool's core behavior in one concrete predicate.

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 second sentence explicitly states when to use it: as the first-pass filter to drop import failures and manual-entry contamination. It gives clear usage context but does not explicitly name alternatives or when not to use it, so it stops short of full routing guidance.

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 burden. It discloses the grouping behavior (returns groups of matching journals) and the exact matching criteria. However, it doesn't disclose what the output format looks like, whether it handles both simple and detailed journal forms consistently, or any edge cases like partial matches or how groups are ordered.

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, focused sentence in Japanese that states the core behavior and matching criteria. It's efficient and front-loaded with the key information. It could arguably add a note about output format, but as-is it's concise and clear.

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 one parameter and no output schema, the description covers the input format and matching logic. However, it doesn't describe the return value structure (what a 'group' looks like), which is important for an agent to use the result. Given the tool's simplicity, this is a moderate 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?

Schema description coverage is 100%, so the schema already documents the journals parameter thoroughly, including both simple and detailed forms. The description adds the matching criteria context but doesn't add new parameter-level meaning beyond what the schema provides. 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 states a specific verb ('detect duplicates'), a resource ('journals'), and the exact matching criteria (date, amount, debit account, credit account all matching). It clearly distinguishes this from sibling tools like benford_analysis or check_balance, though it doesn't explicitly name 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?

The description implies when to use this tool: when you need to find journal entries that are exact duplicates across four fields. However, it doesn't explicitly state when not to use it or mention alternatives like screen_journals for reviewing entries. The usage context is clear but not fully elaborated.

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 of behavioral disclosure. It conveys the core behavior — a read operation that returns a list with explanatory text — but offers no detail about response shape, ordering, or whether the rule set is complete. For a simple listing tool this is adequate but not rich.

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 no filler, and the action plus object are front-loaded. 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 zero-parameter listing tool with no output schema and no annotations, the description covers the essential facts: what is returned and what each list entry means. It could note how this fits the screening workflow (e.g., reading rules before running screen_journals), but nothing critical for invoking the tool correctly is missing.

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 declares zero parameters, so the baseline is 4; there are no arguments the description needs to clarify. The sentence appropriately refers only to the returned list and its explanations, which is all the schema requires.

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 uses a specific verb ('returns') and resource ('list of implemented screening rules'), and adds what each item contains ('description of what each indicates'). It is implicitly distinct from siblings like screen_journals, benford_analysis, and detect_duplicates, which appear to run analyses rather than enumerate rules, though this distinction is not stated 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?

No guidance is given on when to use this tool versus the sibling screening tools, and no exclusions or conditions are mentioned. An agent must infer that list_rules is a discovery or prerequisite step before running the screening tools.

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 must disclose behavior itself. It discloses that detection is not evidence of fraud and that it returns a sorted list. However, it does not state that the operation is read-only/non-destructive, does not describe pagination or truncation via the 'top' parameter, and gives no detail on the output structure (e.g., risk scores, matched rules). The caveat is useful, but more behavioral context is missing.

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, front-loaded with the primary action and outcome, then a critical caveat. There is no redundancy or filler; every sentence earns its place. The caveat is placed at the end, which does not obscure the main purpose.

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 a complex nested options object and no output schema, the description does not describe the return format (e.g., whether it includes risk scores, rule triggers, or just the sorted journals). It also does not mention that it accepts both simple and detailed journal formats (though the schema covers this). The description is adequate for a basic understanding but lacks details needed for an agent to interpret results correctly.

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 mentions applying rules to journal data but does not elaborate on the 'top' or 'options' parameters beyond what the schema already documents. It adds no additional semantic value to parameter usage.

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 it applies all rules to journal data, sorts by risk score descending, and returns results. It positions itself as a primary screening tool distinct from sibling tools like check_balance or detect_duplicates, which are more targeted. The phrase '仕訳データに全ルールを適用し' makes the action and resource explicit.

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 gives context as a '一次スクリーニング' (primary screening) for narrowing what humans should review first, implying it is the initial step. However, it does not explicitly mention when to avoid using it or direct the agent to specific siblings for narrower analyses (e.g., detect_duplicates for duplicate checks). Guidance is implied but not explicit.

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