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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond that: return shape ('type, confidence score, and character positions'), model default and language coverage (CoNLL-2003, English), and the API transport ('HuggingFace Inference API'). No contradiction with annotations.

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?

Three sentences, each earning its place: purpose and entity types, return format, and model/use-case context. Information is front-loaded and there is zero 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 an output schema present and safety profile covered by annotations, the description is complete: it explains the task, the output shape, the default model, language scope, and typical applications. No critical information needed for correct invocation is missing.

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% and both parameters are already well documented (text with length limit, model with default and alternatives). The description does not add unique parameter semantics beyond what the schema provides, landing at the baseline for high coverage.

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 uses a specific verb ('Extract') and clear resource ('named entities') with explicit entity types (PER, LOC, ORG, MISC). It differentiates itself from sibling NLP tools (sentiment, summarize, translate, zero_shot) by focusing on NER and even naming the underlying BERT model.

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?

Provides clear context by listing concrete use cases ('document parsing, contact extraction, and knowledge graph construction') and stating the default model handles English NER. However, it does not explicitly mention when not to use it or point to specific alternative sibling tools, so it stops short of full when/when-not guidance.

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