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

With no annotations, the description carries the full burden and does meaningful work: it discloses determinism ('same input, same output'), the latency profile ('in milliseconds'), and that no LLM call is involved — all traits an agent cannot infer from the empty schema. It does not cover failure modes, input size limits, or behavior when no entities match, which keeps it out of 5 territory.

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?

Front-loaded with the core verb-resource-output framing, then the positioning, then the supported entity list. The enumeration of extraction types is long but directly aids tool selection, so it earns its place; a slight trim would make it tighter.

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?

There is no output schema, so the description must describe returns — and it does ('strict, machine-readable JSON', 'exactly the fields you need'). Combined with the stated determinism and supported entity types, an agent has enough to call it correctly, though input limits and empty-match behavior remain unaddressed.

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 0%, so the description must compensate for three bare parameters. It explains the intent of the two optional ones ('pass fields or a JSON schema to receive exactly the fields you need') and implies 'text' is the source input, but never states the expected shape of 'fields' (array of strings) or 'schema' (a JSON schema object), leaving the schema's type-only definitions to do that work.

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?

States a concrete verb and resource ('Turn unstructured text into strict, machine-readable JSON') plus the exact extraction categories it supports. The positioning as 'a deterministic, reproducible alternative to an LLM extraction call' makes it unmistakable against siblings like web-search or token-risk-summary, which do entirely different things.

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?

Gives clear context for when to reach for it: agent pipelines needing reproducible structured output from invoices, emails, messages, logs or documents, and the 'pass fields or a JSON schema' instruction tells the agent how to steer results. It stops short of explicit when-not-to-use guidance or naming an alternative tool to use instead.

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