sanctions-screening

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

No annotations provided, so description carries full burden. Discloses date and cost, but does not explain side effects, permissions, or response behavior beyond classification. 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?

Three sentences with no redundant information. Essential facts (input, output type, date, cost) are efficiently front-loaded.

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 no output schema, the description omits what the classification result looks like (e.g., risk level, list names). This may require the agent to infer or call the tool to discover the response format. Could be more 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?

Schema coverage is 50% (only api_key documented). Description adds meaning for 'country' by specifying it accepts ISO alpha-2 or name, which is critical for correct usage. api_key is already well-documented in 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 clearly states the tool classifies AML risk against FATF and EU lists, accepts specific input formats (ISO code or country name), and includes a date and cost. This distinguishes it from siblings like kyb_check or screen_name.

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 usage through its specific purpose but does not explicitly state when to use this tool vs alternatives or provide when-not scenarios. Cost mention provides some context but not comparative 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 full burden. It mentions 'free trial credit' but does not disclose limits, idempotency, costs after trial, or whether the action is reversible. Lacks behavioral details for a creation tool.

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 fluff. Every word adds value. Perfectly concise and front-loaded.

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 simple tool with one optional parameter and no output schema, the description covers the core purpose and high-level use. However, it omits return value, error cases, and how to use the key after creation.

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% (no descriptions in schema). The description does not mention the 'note' parameter, leaving its purpose and constraints unexplained. The agent must infer from the schema 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 action ('Create a Watchtower API key') and includes context ('with free trial credit'). It distinguishes itself from all sibling tools, none of which deal with API keys.

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 that the key is needed for screening tools ('Store the key; screening tools require it'), but does not explicitly state when to use vs. not use, or provide prerequisites or 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?

With no annotations, the description carries full burden. It discloses monitoring behavior, webhook posting, cost ($0.01/day), prepaid debit from API key credit, max 90 days, and automatic trial key creation. It does not mention deletion or expiration handling, but covers core behavioral aspects well.

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, each adding distinct value: main function, event posting, and pricing/duration. It is front-loaded and contains no redundant 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 complexity (5 parameters, no output schema), the description covers the key aspects: purpose, behavior, cost, and limits. However, it lacks detail on parameters like threshold and days, and does not describe the response format. Still, it provides sufficient context for most use cases.

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 only 20% (only api_key has a description). The description does not explain the meaning of days, threshold, name, or webhook_url beyond the overall purpose. It fails to compensate for the low schema coverage, leaving parameter semantics unclear.

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 monitors a name against sanctions and export-control lists, and distinguishes it from one-time screening tools like screen_name. It includes specific details about webhook event posting and pricing, making the purpose unambiguous.

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 explains when to use the tool (to monitor a name) and what happens (webhook on daily list refresh). It does not explicitly mention alternatives or when not to use it, but the context and sibling tool names (e.g., screen_name) imply the distinction. Slightly lacking explicit exclusion 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?

The description discloses that the tool is 'Free:' (no cost), and the listed outputs (versions, hashes, etc.) indicate a read-only, non-destructive behavior. With no annotations provided, the description adequately conveys the tool's behavioral profile.

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 that efficiently covers all key aspects of the tool's functionality without any redundant 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 zero parameters and no output schema, the description fully characterizes what the tool does and returns, leaving no ambiguity about its purpose or output.

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?

There are zero parameters, and the description adds meaning by specifying exactly what the tool returns (versions, hashes, freshness, counts, prices), which goes beyond the empty schema to inform the user of the expected output.

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 provides 'sanctions list versions, source hashes, freshness, entry counts, and the full per-tool price menu,' which is a specific verb+resource combination that clearly distinguishes it from sibling tools like screen_name or kyb_check.

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 guidance on when to use or not use this tool is provided. However, its purpose as a free information retrieval tool is implied by the prefix 'Free:' and the listing of data it returns.

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 cost and the combined operation but does not specify side effects, idempotency, or required permissions. The cost disclosure is a positive, but lack of behavioral details keeps the score at 3.

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, followed by cost. Every part adds value; 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?

The tool has no output schema and no annotations. The description covers purpose, parameters implicitly, and cost, but it does not describe the return format or any result details, leaving a gap for a tool of moderate complexity.

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%), with only api_key having a description. The description clarifies that 'lei' and 'name' are alternative identifiers for the company, adding meaning beyond the schema. However, it does not fully compensate for the lack of descriptions on all 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 tool resolves a company to its GLEIF legal identity and screens against sanctions, combining two functions. This distinguishes it from siblings like resolve_lei (single step) and screen_name (screening only). Verb 'resolve' and 'screen' are specific.

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 it does both tasks 'in one call' and costs $0.02, guiding users to use it when they need combined resolution and screening. It does not explicitly exclude alternatives but context implies it replaces separate calls.

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. It only mentions 'free' but lacks details on authorization (api_key is required but not described), rate limits, or behavior when no watches exist.

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?

Extremely short, but at the expense of useful information. The single sentence is too sparse to be 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?

The tool is simple (one param, no output schema), but the description omits any mention of output format, pagination, or limits. It feels incomplete for practical 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 coverage is 0%, so the description must compensate. It fails to describe the only parameter 'api_key' – no hint on what it is or how to obtain it.

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 ('list') and resource ('active watches'), and the 'free' qualifier adds a small distinction. However, it doesn't explain what a 'watch' is beyond the tool name.

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 siblings like 'create_watch' or 'screen_name'. No indications of prerequisites or 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?

No annotations provided, so description must fully disclose behavior. Mentions checksum validation and cost, but does not describe error cases, authorization requirements (api_key optional, explained in schema), or rate limits. Adequate but not comprehensive.

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, no wasted words. Front-loaded with purpose and key details.

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, so description should specify return structure more clearly. Lists fields but not their nesting or types. Missing error handling info. Sufficient for simple use but not 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?

Schema coverage is 50% (api_key described). Description adds that LEI is checksum-validated first, which is useful. However, no additional detail on lei format beyond schema constraints. 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?

Clear verb 'resolve' and resource 'LEI to official GLEIF record'. Lists returned fields: legal name, status, jurisdiction, country, registration status. Distinct from sibling search_lei_by_name which searches by name.

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?

States cost ($0.01 per call) and checksum validation, implying usage when you have an LEI string. However, no explicit when-not-to-use or alternative tools mentioned.

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; description discloses determinism, return structure (findings, counts, redacted copy), and cost ($0.005/call). Could add whether the original text is modified, but 'redacted copy' implies immutability.

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 efficient sentence listing supported PII types, followed by two short sentences on behavior and usage. No redundant or verbose text.

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 no output schema, description fully covers return values (findings, counts, redacted copy) and cost. All necessary details for invocation are present.

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 50%; description lists input 'text' meaning implicitly. Schema describes api_key well; descriptions adds no new param semantics beyond listing PII types. Meets baseline for minimal addition.

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 detects and redacts PII and secrets, with a long list of examples. Distinguishes from sibling tools like screen_name or kyb_check which have different purposes.

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 advises use before logging/forwarding untrusted text. Lacks explicit exclusion of alternative tools, but sibling context makes it clear this is for textual PII scanning.

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 must cover behavior. It discloses cost, exact match logic, and the behavior of the api_key parameter (optional, auto-creation, reuse). It does not detail rate limits or error handling, but sufficiently covers key behavioral aspects.

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 plus cost note, which is efficient and front-loaded. While it could be structured, it contains no wasted words and is 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?

The tool has two parameters and no output schema. The description omits details on return values (e.g., whether output is a boolean or risk score). It is adequate for basic use but lacks information on response structure, which an agent might need.

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 50%: api_key has a detailed description, but address has none. The tool description adds context on matching (exact) but does not clarify address format or specifics beyond the schema constraints. Baseline 3 is appropriate as schema partially compensates.

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 checks a crypto address against OFAC's sanctioned list, specifying exact match. It uses a specific verb (check) and resource (crypto address), distinguishing it from siblings like screen_name or check_jurisdiction.

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 tells when to use: for checking crypto addresses for sanctions. It mentions cost and exact match, but does not explicitly state when not to use or compare to alternatives. However, the single-purpose nature makes usage clear.

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 discloses key behaviors: deterministic, typo-tolerant fuzzy matching, cost of $0.02 per call, and API key management (optional trial key auto-creation). It does not mention rate limits or error handling, but overall provides substantial 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 sentences effectively convey purpose, target lists, matching behavior, cost, and API key handling. Front-loaded with key information, 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?

For a tool with 6 parameters and no output schema, the description covers purpose, behavior, cost, and some parameter context. It is sufficient for basic usage but could explain the 'types' and 'threshold' parameters more fully. Lacks output format, but compensated by no 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?

Schema description coverage is 50% (3 of 6 parameters have descriptions). The description adds value by explaining typo-tolerant matching, which contextualizes the threshold parameter, but does not detail the 'types' or 'threshold' beyond schema. Meets baseline with some additive context.

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 screens names against a comprehensive list of sanctions and exclusion databases, specifies the verb 'Screen' and the resource 'person/company/vessel name', and differentiates from sibling tools by focusing on single name screening with fuzzy matching.

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 cost and API key handling but does not explicitly state when to use this tool versus alternatives like screen_names_batch or check_jurisdiction. It implies single name screening but lacks clear usage context or exclusions.

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 exist, so the description carries the burden. It discloses pricing and billing (debited from API credit), but does not mention rate limits, idempotency, or error handling. The behavior of screening against multiple lists is clear.

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, each earning its place: first sentence states action and lists, second sentence adds pricing. No redundant words. Front-loaded with 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?

Given 3 parameters and no output schema, the description is incomplete. It does not explain what the threshold parameter does (minimum match confidence) nor what the response format contains (matches, scores, etc.). The agent may not know how to interpret results or set the threshold.

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 33% (only api_key described). The description adds no detail about the threshold parameter or names format. It only reiterates the max batch size (500) already in schema. The agent gets no additional meaning beyond the schema for the 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 tool screens up to 500 names against multiple specific sanctions lists (OFAC, UN, EU, UK OFSI). This distinguishes it from sibling tools like screen_name (single name) and other unrelated tools. The verb 'Screen' and resource 'names' are specific.

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 cost savings (25% below single-call price) implying batch use is cheaper, but does not explicitly state when to use this tool versus screen_name or other tools. No guidance on prerequisites or alternatives is 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?

No annotations are provided, so the description carries full burden for behavioral disclosure. It only mentions cost and return fields, lacking details on rate limits, authentication (though api_key is optional), quotas, or error handling. This is insufficient for a tool without annotations.

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 includes the essential purpose and cost. Every word adds value, with no redundancy or fluff.

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 absence of an output schema, the description lists return fields but not their types or error behavior. It misses details like what happens when no results are found or the behavior of the trial_api_key. Adequate but not fully 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?

With only 33% schema description coverage, the description adds minimal meaning beyond the schema. It implies that 'name' is the company legal name and 'limit' controls result count, but does not fully compensate for the undocumented parameters. The api_key parameter is well-described in the 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 clearly states the tool's purpose: to find Legal Entity Identifiers by company legal name via GLEIF, returning specific fields. It uses a specific verb and resource, and distinguishes from sibling tools like resolve_lei by focusing on search by name.

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 the cost per call but does not explicitly state when to use this tool versus alternatives, nor does it provide prerequisites or exclusions. Usage context 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.

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

No annotations provided, so the description carries full burden. It discloses the tool is deterministic and costs money, but does not mention authentication beyond the optional api_key, error handling for invalid inputs, or rate limits. It could be more transparent about side effects (none) and return behavior.

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 efficiently convey purpose, supported types, auto-detection, and cost. No wasted words; information is 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?

Given 3 parameters and no output schema, the description covers tool purpose, types, and cost. However, it does not specify the return format or structure (e.g., normalized identifier, status), leaving some ambiguity about output behavior.

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 33% (only api_key described). Description adds that type is auto-detected if omitted and value is the identifier to validate, which provides meaning beyond schema enum and type string. However, value lacks explicit description in both schema and description beyond implication.

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: deterministically validate and normalize identifiers by checksum/format. It lists 15 supported types (e.g., iban, lei, isin) and mentions auto-detection if type is omitted. This distinguishes it from sibling tools like check_jurisdiction or resolve_lei.

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 (validate/normalize identifiers) and costs $0.005 per call, but does not explicitly state when not to use or mention alternatives. However, the sibling tool list provides context for related functionality.

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