dakera_extract

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

With no annotations, the description carries full responsibility for behavioral disclosure. It explicitly states that api_key is 'Never persisted — used for this request only', and explains the resolution hierarchy (per-request override → namespace default → server default → GLiNER local). It also notes that entity_types are used only when provider is gliner. These details surface important behavioral traits.

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. It uses a colon to list the extracted information types and an arrow notation to concisely convey the resolution order. The list of supported providers is compact and informative. No redundant verbiage.

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 of the tool (nested override object, provider hierarchy, multiple providers), the description covers the essential operational details. It explains the provider resolution order, the role of namespace, and the persistence behavior of api_key. While it doesn't describe the output format or error scenarios, these are not explicitly required by any output schema or annotation.

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% with each parameter described. The description adds meaningful context beyond the schema: it explains the provider override hierarchy, the namespace default behavior, and the conditional use of entity_types. The extractor_override nested object is also well-documented with its own description.

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's purpose: 'Extract structured information (entities, topics, key phrases, summary) from arbitrary text'. The verb 'extract' and the specific resource (text) make the action unambiguous. It distinguishes itself from sibling tools by focusing on extraction rather than search, store, or recall operations.

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 detailed guidance on when and how to use the tool, explaining the provider resolution hierarchy and listing supported providers. It clarifies that entity_types are only used with GLiNER and that api_key is request-scoped. While it doesn't explicitly contrast with alternatives, the provider hierarchy and parameter conditions give clear usage context.

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