Compliance Engine

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

No annotations are provided, so the description carries the full behavioral burden. It hints that this is a read-style lookup and gives dataset size and return fields, but says nothing about authentication, rate limits, pagination, or the matching behavior implied by the threshold 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?

Two tight sentences with zero filler, and the core action plus data source are front-loaded. It is appropriately sized for a simple lookup tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully names the returned fields (LEI, legal name, jurisdiction), which is a real contribution. However, it omits the retrieval/matching context and sibling routing an agent would need, so it is adequate 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 100%, so both the query and threshold parameters are already documented in the schema, including the 0-1 range and 0.82 default. The description adds nothing about parameter syntax or matching behavior, so the baseline 3 applies.

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 (Search) and resource (legal entities) and adds the data source (GLEIF, 20K+ records). It clearly reads as an entity-lookup tool, but it never names its siblings check_pep and check_sanctions, so differentiation is left to inference.

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?

There is no when-to-use guidance and no mention of alternatives like check_pep or check_sanctions, despite those siblings covering adjacent screening tasks. An agent must guess whether to run an entity lookup versus a PEP or sanctions check.

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 does disclose the data provenance and coverage ('11.7K+ PEP records from Wikidata'), which usefully signals that a negative result only means 'not in this dataset'. It says nothing about match semantics, whether the call is read-only, rate limits, or how threshold affects 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 tight sentences with the purpose front-loaded and the coverage caveat second. No filler, no restatement of the tool name.

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?

This is a screening tool with no output schema and no annotations, so the description needs to say what a result looks like (boolean, match score, candidate list) and what a miss implies. It only hints at dataset scope and never describes the return value, leaving a real gap for callers.

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 both 'query' and 'threshold' (including the 0.82 default) are already documented in the schema. The description adds no extra meaning such as name-format expectations or how lowering the threshold changes results, so the baseline 3 applies.

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?

States a specific verb ('Check') plus the exact resource ('Politically Exposed Person (PEP)') and even names the backing data source. 'PEP' versus the sibling names check_sanctions and check_entity is enough for an agent to route correctly without opening a schema.

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?

There is no when-to-use or when-not-to-use guidance, and no mention of the obvious alternatives (check_sanctions for sanctions lists, check_entity for general lookups). The agent must infer that PEP screening is a distinct check from sanctions screening.

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. It does disclose the return shape (matches with confidence scores), which is genuinely useful, but says nothing about read-only nature, rate limits, result completeness, or how threshold affects output. Adequate but with clear gaps for an unannotated 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 tight sentences, front-loaded with the core action and list coverage, followed by the return behavior. Every sentence earns its place with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description steps in to state what is returned (matches with confidence scores) and which lists are consulted. It is close to complete for a 3-param lookup tool, though it could say more about threshold behavior and result limits.

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 query, limit, and threshold are all documented in the schema (including defaults and the 0-1 range). The description's mention of confidence scores loosely ties to threshold but adds no syntax or behavioral detail beyond the schema, so the baseline 3 applies.

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 gives a specific verb ("screen") and resource (person or entity against global sanctions lists) and even enumerates the exact lists checked (OFAC SDN, UK OFSI, EU Consolidated, UN Consolidated). It stops short of explicitly distinguishing itself from siblings check_pep and check_entity, though naming sanctions lists implicitly separates it from PEP 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?

Usage is only implied: an agent can infer this tool is for sanctions screening, but there is no statement of when to choose it over check_pep or check_entity, nor any exclusion criteria. For a tool sitting in a family of three screening tools, that routing guidance is missing.

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