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

With no annotations, the description carries the full burden and does disclose meaningful behavior beyond the schema: per-call cost for each mode, subscription coverage for standard, and the extra entity classes deep produces (currencies, organizations, person names, embedded JSON). It does not mention latency, failure behavior past the 20k limit, or whether results are persisted.

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 dense sentences, front-loaded with the core action, then mode economics, then the optional flag. Every sentence informs a calling decision, though the pricing detail is slightly verbose relative to the extraction guidance.

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 3-parameter tool with no output schema and no annotations, the description covers cost, mode differences, and the optional flag well. The main gap is that it never enumerates what the default standard mode extracts, leaving the baseline output shape only partially characterized.

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%, so baseline would be 3, but the description adds real meaning the schema lacks: it quantifies what each mode returns and what the cost tradeoff is, and clarifies include_referrals as an append operation. That goes beyond the schema's bare 'Tier' and 'Append complementary service suggestions'.

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 specific verb and resource ('Extract structured entities from unstructured text') and immediately differentiates the two modes, which is exactly what distinguishes it from the sibling text.structure.deep. An agent can tell what it does and which tier it is choosing 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 gives mode-selection context (cost, and what deep adds) and explains include_referrals, which is implied guidance for parameter choice. However, it never says when to prefer this tool over alternatives such as extract.and.summarize, extract.verified, or text.structure.deep as a separate tool; usage must be inferred from the mode pricing.

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