Field extraction

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

Annotations already carry the safety profile (not read-only, not idempotent, open world), and the description adds genuinely new behavioral context: it 'costs credits from the account wallet' and returns 'typed values with confidence.' The cost disclosure is especially valuable because readOnlyHint=false alone would not tell an agent this operation has a wallet charge. 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 short sentences, each carrying a distinct fact: the extraction action, the typed-value return contract, and the cost. The core purpose is front-loaded in the first sentence and there is zero filler or repetition of what annotations already state.

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 a flat 3-parameter schema, no output schema, and safety covered by annotations, the description addresses purpose, cost, and output flavor ('typed values with confidence'). It stops short of describing the exact response shape or behavior on unresolvable fields, but those gaps are 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 coverage is 67%, and the required 'text' property has no schema description; the description compensates by defining it as 'any block of text.' The phrase 'you name the fields' clarifies that the enum-less 'fields' array holds arbitrary user-chosen keys, which is meaning beyond the schema's 'The field names to pull out.' The 'instructions' param is already self-described ('Optional extra guidance'), so no prose needed.

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 action ('Pull... out'), a concrete resource ('a field set you define' from 'any block of text'), and the core contract ('you get typed values with confidence'). It clearly goes beyond the tautological title 'Field extraction' by explaining the user-defined schema model. However, it never names any sibling (e.g., parserail_parse, parserail_invoice) to state what it is not, so sibling differentiation is implicit rather than explicit.

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 phrase 'any block of text' combined with 'a field set you define' implies the general-purpose case: use this when you need custom fields not covered by a domain-specific tool. But the description never states when not to use it or points to alternatives among the 41 siblings, so the routing guidance is left mostly to inference.

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