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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds value beyond these by disclosing sub-50ms latency and the BERT-NER model basis, as well as providing a detailed return structure with confidence scores. This supplemental context enriches the agent's understanding without contradicting 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?

The description is well-structured: a clear opening sentence, a brief method note, and a systematic Args/Returns section. It is longer than strictly necessary, but given the absence of an output schema, the detailed return documentation is justified. The core purpose is front-loaded, making it scannable for an agent.

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 fully specifies the return dictionary structure, including entity fields, types, offsets, and confidence scores. Given the single parameter and simple input, the description covers all necessary context an agent needs to call the tool and interpret results. Combined with annotations, this is complete.

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% and the schema already describes the 'text' parameter. The description restates the arg without adding new semantic detail (e.g., encoding, preprocessing). Per the rubric, a baseline of 3 is appropriate when the schema fully documents the parameter and the description adds no additional meaning.

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 opens with a specific verb and resource ('Extract named entities (NER) from text') and explicitly lists the entity types (persons, organizations, locations, miscellaneous). This clearly differentiates it from siblings like extract_key_phrases and detect_pii, which target different tasks. The purpose is unmistakable even without opening the schema.

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 does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions or prerequisites. However, the clear purpose implies the appropriate use case (entity extraction), and the sibling list offers context. Since no explicit guidance is given, it falls to implied usage, warranting a 3.

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