semantic_search

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

No annotations are provided, so the description carries full burden. It discloses risk-list bias with measured statistics (embedded 990,055 of 47,486,969, ratio 0.0208; ~99.6% risk-listed, ~97% natural persons), a verified example ('sanctioned russian aluminium holding' returned RU sanctioned ships), the authoritative and moving `coverage` object, and latency (6.4s cold). This is far beyond typical 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 dense but front-loaded: first sentence states purpose, then filters and return fields, followed by caveats, usage guidance, and latency. Each sentence contributes a distinct fact (mechanism, bias, coverage, paired tool, performance). 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 there is no output schema and no annotations, the description fully compensates: it names return fields, the `coverage` object, limitations of the embedded slice, the need to pair with search_entities, and latency. This is enough for an agent to decide whether and how to call the 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 100%, so the baseline is 3. The description reinforces kind values (Company/Person/Asset) and jurisdiction as ISO code, and gives a natural-language query example, but it adds little meaning beyond the schema's parameter descriptions. No contradiction or missing parameter 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?

Description opens with a specific verb and resource: 'Meaning-based entity search over the corpus (BGE-M3 vector ANN over the resolved dossier cards).' It clearly states what it finds (companies and people semantically closest to a natural-language query) and differentiates itself from lexical sibling search_entities. It also names return fields and how to chain results into get_dossier / trace_ownership_path.

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 instructs when to use this tool versus alternatives: 'ALWAYS pair this with search_entities, which is lexical and covers the full corpus, before concluding anything about an entity's existence.' It also explains that an empty or off-target result means 'not embedded yet' far more often than 'not found', guiding the agent's interpretation and fallback behavior.

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