Find the data behind a concept

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

Beyond annotations, the description discloses that the tool is read-only with no LLM cost, performs semantic + lexical retrieval, can resolve concepts even when the field is captured under a different name, and restricts document_ids as a hard server-side scope. It also explains the ranked output structure, adding meaningful behavioral context beyond the safety hints already present.

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 long but densely structured with clear USE WHEN, NOT FOR, ARGS, and RETURNS sections. Every section earns its place, and the core purpose is front-loaded. The formatting makes it easy for an agent to scan and extract invocation decisions quickly.

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 thoroughly covers return value shape: ranked FIELDS, VALUES, DOCUMENTS, and PASSAGES planes, including key fields and sample values. It also covers all parameters, usage context, exclusions, and safety behavior, leaving little ambiguity for an agent deciding whether and how to call this 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 coverage is 100%, so the baseline is 3, but the description adds value by clarifying query should be in the user's own words, stating top_k's default of 10, and emphasizing that document_ids is a hard scope enforced server-side. These details go beyond the schema's type and constraints.

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 and resource: locate the real data behind a natural-language concept using semantic and lexical retrieval, mapping phrases to fields, values, documents, and passages. It clearly distinguishes this discovery tool from siblings by framing it as the pre-query resolution step and by noting it works even when fields are named differently.

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 explicit USE WHEN conditions: uncertainty about which field holds a concept, empty or ambiguous results from talonic_list_fields/talonic_search, or when answers may live in prose. It also gives NOT FOR exclusions naming talonic_field_values and talonic_filter, making alternative selection unambiguous.

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