ai_extract

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

With no annotations, the description carries the full load, and it does disclose the meaningful behavioral trait that extraction is regex-based rather than model-based, implying pattern-bound recall and possible misses. It does not state whether missing param defaults are applied, how no-match cases behave, or that the operation is a pure read of supplied text. An output schema exists, so return shape need not be covered.

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?

One sentence, front-loaded with the action and finished with the decisive constraint. No filler, no repetition of the tool name.

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?

For a two-parameter tool with an output schema, the definition covers what is extracted, by what mechanism, and the allowed kinds. The only shortfall is the absence of guidance on the text input's expected scope or size, which is minor given the tool's simplicity.

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% and the schema declares no enum for kind, so the description's inline enumeration {emails, urls, phones, numbers} is the only source of valid values — real added meaning. The text parameter is left unexplained, though its purpose is largely self-evident from the name and the required flag.

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 names a specific verb (Extract) and resource (entities) and closes with the four supported kinds, which distinguishes it from siblings like ai_keywords or ai_sentiment. It stops short of stating scope or exclusions (e.g., single text vs. bulk), so it is clear but not fully discriminating.

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?

Usage is only implied: the kind enumeration hints that you call this when you want patterned entities rather than semantic keywords, but the description never says when to prefer it over ai_keywords or when not to use it. No prerequisites or exclusions are given.

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