netintel_text_to_json

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

With no annotations, the description carries the full burden. It usefully discloses the underlying model (Claude Haiku) and that values are 'pulled from the text and coerced' to the declared types, which is real behavioral context beyond the schema. It is silent on failure modes (what happens when a requested field is absent), cost/latency, and any input limits, and the text is visibly truncated mid-sentence.

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?

A single front-loaded sentence states the transformation, the conformance contract, and the engine, with little waste. The trailing ellipsis indicates the description is truncated, which slightly undercuts an otherwise tight structure.

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 tool with two required params (one nested), zero schema coverage, no annotations, and no output schema, the description covers purpose and rough mechanics but omits the schema-parameter format, failure behavior when fields cannot be extracted, and any sense of the output shape. It is minimally viable but leaves gaps an agent must discover by trial.

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. It does explain the intent of both parameters — 'text' is the unstructured source and 'schema' is the caller-declared set of fields and types — which is more than the bare schema offers. However, for a nested object parameter it never states the expected format of the schema value (JSON Schema vs. a custom shorthand), leaving a critical ambiguity unresolved.

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 and resource ('turn unstructured text into structured JSON') and adds the key qualifier that output conforms to a caller-supplied schema, which distinguishes it from fixed-schema extractors like netintel_extract_invoice. It does not, however, differentiate itself from close siblings such as netintel_schema_parse, netintel_json, or netintel_schema_map, so an agent still has to guess which of several similar tools applies.

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?

There is no when-to-use or when-not-to-use guidance, no mention of alternatives among the many schema/extract siblings, and no prerequisites. The phrase 'the agent declares the fields and types it wants' hints at the calling pattern but gives no conditions for choosing this tool over netintel_extract or netintel_schema_parse.

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