netintel_json

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

With no annotations, the description carries the full behavioral burden, and it does disclose one meaningful trait: a deterministic tokenizer runs first at no LLM cost, implying an optional paid LLM path. It says nothing about failure behavior on unrepairable input, idempotency, or what is returned when repairs are partial.

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 and dense: purpose first, then the defect list, then the execution/cost note. The single long enumerated sentence is efficient, though it reads as a list dump and the trailing "with an…" shows the content is cut off mid-clause.

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 4-parameter tool with zero annotation coverage, 0% schema coverage, a nested-object parameter, and no output schema, the description should at minimum explain `coerce`/`schema` and the shape of success vs. failure. It covers the repair domain well but leaves roughly half the calling contract undocumented.

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% across 4 parameters, so the description must compensate, and it only gestures at two: `input` (malformed JSON) and `allow_llm` (via the no-LLM-cost tokenizer note). `coerce` and `schema` — including the nested object structure — are never explained, leaving their semantics entirely opaque.

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 precise verb+resource ("Repair malformed JSON into valid JSON") and enumerates the exact defect classes handled — code fences, trailing commas, single quotes, unquoted keys, bad escapes, duplicate keys, truncation, JSON buried in prose. That enumeration functionally separates it from conversion/extraction siblings such as netintel_text_to_json or netintel_extract, even though none are named.

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 input is evidently malformed JSON text. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g. text_to_json for clean prose-to-JSON conversion). The mention that a deterministic tokenizer runs first hints at the cost tradeoff but is not framed as guidance.

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