sanctions-screening

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

With no annotations, the description carries full burden. It discloses cost ($0.005/call) and data date (2026-02-13), adding useful behavioral context. It does not mention auth requirements for api_key or rate limits, but the cost disclosure is valuable.

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 wasted words, front-loading the core function. Every 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?

No output schema, and description does not hint at return format (e.g., risk level, list status). For a classification tool, this is a moderate gap given 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?

Schema coverage is 0% with 2 params. Description adds meaning for 'country' (ISO alpha-2 or name), but 'api_key' is not described. This is partial compensation.

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 a country's AML risk against FATF black/grey lists and EU high-risk-third-countries list, with specific input format (ISO code or name). This is a specific verb+resource that 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?

The description implies usage for AML risk classification, but does not explicitly state when not to use or mention alternatives. However, the purpose is clear enough for an agent to decide.

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 must cover behavior. It mentions creation and free trial credit but lacks details on idempotency, limits, or retrieval of the key.

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 efficient sentences: first states purpose and feature, second gives critical usage instruction. 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 no output schema and incomplete parameter info, the description is adequate but leaves gaps such as response structure and key limitations.

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 has one optional parameter 'note' with 0% coverage; the description does not explain its purpose or 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 creates a Watchtower API key with free trial credit, distinguishing it from sibling tools that focus on watching or screening.

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?

It advises to store the key for use with screening tools, providing clear usage context though without explicit when-not-to-use 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?

With no annotations, the description carries full burden. It discloses cost ($0.01/day, prepaid), maximum duration (90 days), and the webhook event. It does not cover cancellation or credit depletion, but the main behavioral traits are transparent.

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 concise sentences with no wasted words. The most critical information is 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 5 parameters, no output schema, and no annotations, the description is incomplete. It lacks details about response format, watch ID, and how to manage or list watches (though 'list_watches' is a sibling).

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 the description only implicitly mentions 'name' and 'webhook_url'. It does not explain 'days', 'api_key', or 'threshold'. The 'api_key' parameter is ambiguous regarding whether it is required.

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 'monitor' and the resource 'a name against all sanctions + US export-control lists'. It distinguishes from sibling tools like 'screen_name' and 'screen_names_batch' by implying ongoing monitoring instead of one-time screening.

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 triggering condition (daily list refresh changes) and the action (POST watch_changed event), but it does not explicitly state when to prefer this tool over alternatives like screen_name. However, the context of monitoring vs. screening is reasonably 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?

No annotations provided, so description must handle behavioral disclosure. It mentions output data but not side effects, permissions, rate limits, or whether the tool is read-only. Lacks behavioral traits beyond listing returned fields.

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, brief and to the point. Front-loads 'Free:' which is a notable qualifier. 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?

Tool has zero parameters and no output schema. Description adequately covers the nature of the output (list of versions, hashes, etc.). For a simple info retrieval tool, this is sufficiently 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?

No parameters exist, so schema covers 100%. Description does not need to add parameter meaning. Baseline 4 applies per instructions.

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 lists specific informational outputs (sanctions list versions, source hashes, freshness, entry counts, price menu), making clear what the tool retrieves. It is distinct from siblings which perform actions like checks and searches.

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. The 'Free:' prefix hints at no cost, but no explicit context for selection or exclusion of other 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?

The description discloses cost ($0.02 per call) and the dual action (resolution + screening), but lacks details on authentication, input constraints (e.g., at least one of name/LEI required), error conditions, or rate limits. Since no annotations are provided, the description carries full burden and is incomplete.

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 the core purpose, 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?

The tool combines two complex operations (resolution and screening) but the description does not mention what the response contains, nor its relationship to sibling tools. Given the absence of an output schema, the description should provide more contextual completeness.

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 description partially explains 'name' and 'lei' parameters via 'by name or LEI', but does not mention the 'api_key' parameter or clarify when to use each. With 0% schema coverage, the description does not fully compensate.

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 ('resolve' and 'screen') and the resource (company by name or LEI), distinguishing it from sibling tools that perform only one of these actions.

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 (for combined identity resolution and screening) but does not explicitly contrast with alternatives like resolve_lei or screen_name, nor provides when-not-to-use conditions.

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 implies a read operation by listing, but does not confirm non-destructiveness, side effects, or authorization needs beyond the required api_key.

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 short sentence, which is concise but lacks structure. It is front-loaded but too terse to be fully informative.

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 only one parameter and no output schema, the description is incomplete. It fails to explain what a 'watch' is or that an api_key is required, limiting an agent's ability to use 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 0%, yet the description adds no meaning about the api_key parameter. It does not mention or explain any 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 verb 'List' and the resource 'active watches', distinguishing it from sibling 'create_watch'. However, it does not explain what a 'watch' is, which might be slightly unclear for new agents.

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. The description only states what it does, with no mention of scenarios 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?

Discloses key behaviors: checksum validation and cost ($0.01 per call). However, with no annotations, it omits error handling (e.g., invalid or expired LEI), authentication requirements, or whether the call is idempotent or read-only.

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 purpose and outputs, followed by validation and cost details. No redundant words, 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?

Adequate for a simple resolver but lacks details on error scenarios, API key handling, and rate limits. Output fields are listed but no description of potential failure modes.

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 0% description coverage for parameters. Description partially compensates by mentioning checksum validation for the 'lei' parameter but provides no detail about the 'api_key' parameter, leaving ambiguity about its necessity or 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 the tool resolves an LEI to its official GLEIF record and lists the specific fields returned (legal name, status, jurisdiction, country, registration status). This distinguishes it from siblings like '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?

The description implies usage when you have an LEI and need its official record but does not explicitly contrast with siblings or state when not to use. The checksum validation hint is useful but not a full guideline.

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 were provided, yet the description details deterministic behavior, output format ('findings (masked), counts, and a redacted copy'), and cost ($0.005 per call). This fully compensates for the lack of 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, dense sentence that front-loads the primary action. Although listing many secret types adds length, each item adds specificity. However, it could be slightly more structured (e.g., separate sentences for parameters).

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 2 parameters and no output schema, the description covers purpose, when to use, behavior, return contents, and cost. The omission of the 'api_key' parameter and lack of explanation about optionality/usage is a notable 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 0% and the description does not mention the 'api_key' parameter at all, only implicitly addresses 'text'. While the purpose is clear, the description fails to explain the role or constraints of the second parameter.

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 'Detect & redact PII and secrets in text' followed by an extensive list of specific types. This verb+resource+scope makes the purpose unmistakable and distinguishes it from siblings like check_jurisdiction 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?

Explicitly states 'Use before logging/forwarding untrusted or agent-generated text.' This provides clear context for when to apply the tool. It does not explicitly exclude other cases but the guidance is strong 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, the description discloses key behaviors: exact match, cost per call, and the specific list checked. It does not cover authentication, rate limits, or error handling, but for a simple check, the disclosed traits are sufficient.

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 redundant information. The first sentence states purpose and scope, the second adds cost. Every word 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 tool's simplicity (2 params, no output schema), the description covers the main aspects: purpose, exact match, cost, and target list. It lacks return value description and error handling, but for a screening tool this is acceptable.

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 two parameters (address and api_key), but the description only implies the address parameter. It does not explain the api_key parameter or provide format details for the address. Since schema description coverage is 0%, the description fails to compensate.

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 'Check' and identifies the resource as 'crypto address (BTC/ETH/others)' with the specific context of 'OFAC's sanctioned digital-currency address list'. It also specifies exact match and cost, distinguishing it from sibling tools 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 this tool (to check against OFAC list) and provides cost context. However, it does not explicitly state when not to use it or name alternatives among siblings, which would move it to a 5.

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 behavioral traits: deterministic matching, typo tolerance, list coverage, and cost per call. It does not contradict any implicit expectations. However, it omits details like rate limits or authentication expectations beyond the api_key parameter.

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 front-loaded with essential information: first sentence lists all screened lists, second sentence describes matching and cost. No filler or 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?

Given the complexity (multiple lists, fuzzy matching, cost) and no output schema, the description provides adequate context for expected use. Lacks details on return format or error handling, but coverage is sufficient for a deterministic screening 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 description coverage is low (33%, only dob and nationality have descriptions). The tool description does not elaborate on parameters like threshold, types, or api_key beyond the schema. For a tool with 6 parameters, the description should compensate but does not, leaving parameter semantics to the sparse 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 screens names against multiple specific sanction and exclusion lists (OFAC, UN, EU, etc.), specifies deterministic and typo-tolerant fuzzy matching, and mentions cost. It effectively distinguishes from sibling tools like screen_crypto_address and screen_names_batch by its focus on name-based multi-list screening.

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 is given on when to use this tool versus siblings (e.g., screen_names_batch for multiple names, or screen_crypto_address for addresses). The description only mentions cost but lacks context on prerequisites, limitations, 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?

No annotations provided, so description must carry behavioral disclosure. It reveals cost, lists specific sanctions sources, and debiting mechanism, but omits rate limits, error handling, and what happens on match/no-match.

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 quickly conveys purpose and pricing, but could be more structured to separate core function from pricing 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?

Given 0% schema coverage and no output schema, the description should explain all inputs and outputs. It fails to describe api_key and threshold parameters and does not mention the response format.

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%, and description adds no explanation for the three parameters (names, api_key, threshold) beyond the schema constraints. The threshold and api_key are not mentioned at all.

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 sanctions lists, with cost per name, and is distinct from the single-call sibling screen_name by mentioning batch and lower price.

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 context for when to use (batch screening for cost savings) but does not explicitly state when not to use 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, description carries full burden. It discloses cost ($0.01/call) and return fields, but lacks details on authentication (api_key param not explained), rate limits, error handling, or whether names are fuzzy-matched. 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?

Single sentence, no fluff. Purpose, data source, return fields, and cost are front-loaded. Every word carries weight.

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, no output schema, and no annotations, the description is somewhat incomplete. It lists return fields but omits parameter details, result limits, pagination, and authentication. Adequate for a simple lookup but could better complement the rich 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 coverage is 0%, so description must compensate. It only implies the 'name' parameter via 'by company legal name'. The 'limit' and 'api_key' parameters are not explained at all—limit's effect on results, api_key's necessity or source. Minimal added value.

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 finds Legal Entity Identifiers by company legal name via GLEIF, lists returned fields, and uses a specific verb+resource pattern. Distinguishes from siblings like screen_name or resolve_lei by mentioning GLEIF and candidate records.

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 (e.g., screen_name for name screening, resolve_lei for exact match). No mention of prerequisites or exclusions. Only cost is mentioned but not contextualized against 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 exist, so the description carries full burden. It discloses deterministic behavior, auto-detection, and cost per call, but lacks information on failure handling, response format, or required authentication context beyond the api_key parameter.

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 listing types and noting cost, with no redundant or irrelevant 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?

The tool has no output schema or annotations, and the description omits return value information (e.g., whether it outputs a normalized string or validation status). The api_key parameter is unexplained, and the normalization aspect is vague.

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 0% description coverage. The description adds value by listing the enum values for the 'type' parameter and noting auto-detection. However, it does not explain the 'value' or 'api_key' parameters, leaving gaps in 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 it validates and normalizes identifiers by checksum/format, listing 15 specific types and mentioning auto-detection. This distinguishes it from sibling tools which focus on screening, jurisdiction, and LEI resolution.

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 cost and auto-detection, but does not explicitly state when to use this tool versus alternatives like screen_name or check_jurisdiction. No exclusions or prerequisites are mentioned.

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