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

While annotations already include openWorldHint=true ama, the description adds critical transparency: the exact coverage level ('~1.9% and growing'), the fact that a lack of results is NOT proof of unknown entity, and the need to pair with lexical search. This goes beyond what annotations convey, providing actionable behavioral context.

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 three concise sentences: purpose, capabilities, and critical caveat. It front-loads the core function, adds the key limitation (partial coverage), and gives actionable advice (pair with lexical search). 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's complexity and the presence of openWorldHint in annotations, the description adds essential context about partial coverage (~1.9%) and explicitly tells users not to interpret empty results as absence. It mentions filters but doesn't detail output format; however, no output schema is providedaint necessary for a search tool. Overall, it's complete enough for confident 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 explain parameters. It mentions 'Optional kind + jurisdiction filters' but does not clarify the meaning or allowed values of 'kind' or 'jurisdiction', and completely omits the 'k' parameter. The 'query' parameter is implied but not explicitly described. This leaves the agent guessing about the parameter semantics beyond the names.

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's a 'Meaning-based entity search' using vector embeddings (BGE-3) over 'resolved dossier cards', distinguishing it from lexical searches. It specifies the resource (companies/people) and the semantic nature. It also contrasts with search_entities (lexical/name), making its unique 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?

Explicitly states when to use (when keyword match fails) and provides direct alternative guidance: 'pair with search_entities (lexical/name) before concluding an entity does not exist.' It also flags partial coverage, telling the agent not to rely solely on this tool for absence conclusions. This is exemplary usage guidance.

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