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

No annotations exist, so the description carries the full burden. It states the tool returns one route and recommended next tool, but lacks details on side effects, authentication requirements, rate limits, or idempotency. The read-only nature is implied but not confirmed.

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: first for purpose, second for usage guidance. No redundant or superfluous information. Highly 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 10 parameters, no schema coverage, and an output schema (not shown), the description provides purpose and usage but omits parameter semantics and behavioral nuances. It is moderately complete for a classification tool but leaves 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%; the description does not explain individual parameters beyond the general notion of query content. The many optional parameters (limit, category, subjects, etc.) are not described, forcing reliance on schema enums 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's purpose: to classify ambiguous AML red flag requests and return a route with recommended next tool. It distinguishes from siblings by specifying when to use (ambiguous requests) and when to skip (specific filters or concrete scenario).

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 provides when-to-use and when-not-to-use guidelines: 'Use it for ambiguous requests; skip it when the user already gives specific metadata filters or a concrete scenario.' This is clear and actionable.

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 full burden. It explains that the tool performs exact matching, not ranked search; defines how category, subjects, and typology_family interact; provides country code translation rules; and notes pagination. It also mentions response includes display hints and markdown_table. This is thorough behavioral 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?

The description is relatively long but every sentence serves a purpose: purpose, usage, parameter explanations, pagination, country codes, alternative tool. It is well-structured and front-loaded with the core purpose. Slight wordiness in examples could be trimmed but overall effective.

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 20 parameters, 0% schema coverage, and no annotations, the description covers the most critical aspects (core parameters, pagination, output format). It assumes an output schema exists, which handles return values. While not exhaustive for every parameter, it provides enough context for correct usage of the tool's main features.

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?

Given 0% schema description coverage, the description must compensate. It explains key parameters (category, subjects, typology_family, regulator_jurisdiction, geographic_footprints) with examples and contrasts. However, many parameters (limit, cursor, detail, regulator, source_id, risk_level, etc.) are not mentioned, leaving gaps. It adds value for the most important ones but is not complete.

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 opens with 'Return AML red flags for exact metadata criteria without ranked relevance search,' clearly stating the verb ('Return'), resource ('AML red flags'), and distinguishing it from the sibling tool search_red_flags. It is specific and leaves no ambiguity about what the tool does.

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 provides usage scenarios ('Use this for exact metadata requests...') and gives concrete examples (e.g., 'high-risk depository structuring red flags'). It also states when to use the alternative tool ('Use search_red_flags instead for open-ended relevance questions') and covers pagination behavior with next_cursor. This is comprehensive 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 provided, so description carries full burden. It mentions returning source and citation metadata but does not disclose authentication needs, rate limits, or error behavior (e.g., missing ID).

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?

Single sentence, highly concise, no wasted words. Front-loaded with the core action.

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 output schema present, return values are covered. However, missing guidance on usage, potential errors, and what 'source and citation metadata' entails reduces completeness for a retrieval 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 coverage is 0%, so description must compensate. It only adds 'by id' but provides no format or constraints for the red_flag_id parameter, missing an opportunity to clarify value semantics.

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?

Description clearly states it returns a single AML red flag by ID, including source and citation metadata. It distinguishes from sibling tools like search_red_flags and filter_red_flags.

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 explicit when to use vs alternatives. The description implies use for fetching one specific flag by ID, but no guidance on not using it for multiple flags or which sibling to use instead.

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, so description carries the burden. Mentions 'bounded detail' but does not explain what 'bounded' means operationally. Does not explicitly state read-only behavior or side effects, though implied by 'return'.

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, front-loaded with action and key details. No unnecessary words. Efficient and easy to parse.

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 output schema exists, return values need not be fully described. Covers key output elements and sibling distinction. Lacks error handling or precondition notes, but acceptable for a simple retrieval 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 has one parameter (source_id) with 0% coverage. Description references source_id but adds no further semantics (e.g., format, source, or how to obtain valid IDs). Adds minimal value beyond the parameter name.

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 verb 'Return' and resource 'one source by source_id'. Lists included elements (citations, metadata, red flag IDs, snippets) and distinguishes from sibling get_red_flag.

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 directs when to use get_red_flag instead for full text, providing a clear alternative. Does not address other siblings or general when-not-to-use scenarios, but sufficient for the simple 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 carries the burden. It explains that the tool returns available filter values and adds semantic clarifications for several fields (e.g., category, subjects, typology_family). This provides useful behavioral context beyond a simple listing.

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 with three sentences: first states the action, second gives usage guidance, third clarifies key field semantics. No wasted words.

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 has no parameters and an output schema exists, the description adequately explains the purpose and some field meanings. It could be more complete by describing the expected output format or mentioning that the output is a list of valid values.

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 no parameters, so the schema coverage is complete. The description adds value by explaining the meaning of the fields that will appear in the output, which compensates for the lack of parameter documentation.

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 lists available filter values for a specific set of fields. While it distinguishes from sibling tools implicitly (sibling tools focus on red flags and sources), it does not explicitly differentiate itself.

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 says to call this before or during consultation when valid local filter values are needed. It provides clear context but does not mention when not to use it or suggest alternatives.

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 does not disclose any behavioral traits (e.g., side effects, authorization, rate limits). For a read-only list tool, the omission is a minor gap but still reduces transparency.

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 with no filler; front-loads the purpose and usage guidance.

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?

Has output schema (not shown) and description lists key elements returned. For a zero-parameter list tool with rich output schema, completeness is high.

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?

Zero parameters (schema coverage 100%), so baseline is 4. No additional parameter meaning needed.

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 explicitly states the tool lists AML red flag source coverage with specific outputs (citation URLs, source counts, aggregate metadata, red flag IDs), and differs from sibling tools like get_source (single source) and search_red_flags.

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?

Includes explicit when-to-use instruction: 'Use when users ask what sources or citations the corpus covers.' Does not specify when not to use, but the context is clear given siblings.

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, so description fully carries the burden. Discloses response format (display hints, markdown table), lack of cursor (increase limit for more results), and explains semantics of key filters like category, subjects, typology_family, regulator_jurisdiction, geographic_footprints.

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?

Relatively long (~300 words) but well-structured with clear sections: purpose, response format, agent guidance. Each sentence adds value; no fluff. Slightly verbose but 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?

Thorough guidance for a tool with 11 parameters, no schema descriptions, and 7 siblings. Covers usage scenarios, parameter semantics, response details, and even country code mappings. Fully compensates for missing schema descriptions.

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%, but description adds significant semantics: explains difference between category, subjects, and typology_family; clarifies regulator_jurisdiction vs geographic_footprints; gives examples of country code translations. Does not cover every parameter individually but compensates well.

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 tool searches AML red flags using natural-language context and optional filters. Differentiates from siblings like classify_red_flag_request, filter_red_flags, and list_filters by specifying distinct use cases.

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?

Provides explicit guidance on when to use this tool vs alternatives: use classify_red_flag_request for ambiguous requests, skip for specific metadata filters; use filter_red_flags for exact metadata; use list_filters for valid values. Also advises on handling vague requests.

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