extract_inferred

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

With no annotations provided, the description carries full burden. It discloses the use of LLM for schema inference, deterministic extraction, dependencies on environment variables, and the cost/consistency benefits. It does not mention potential failure modes, but overall provides good behavioral insight beyond just the basic purpose.

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?

The description is concise (3 sentences) and front-loaded with key information: the core behavior, comparison to alternatives, and configuration requirements. Every sentence adds value with no redundancy.

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?

The description covers the tool's purpose, mechanism, comparison to a sibling, and configuration needs. It mentions the output format (JSON Lines). However, it does not address what happens on failure (e.g., if LLM call fails or page is inaccessible) or provide details on error handling. Minor gap for a tool with no output schema.

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%; the schema already describes each parameter. The description mentions the goal parameter ('optionally steered by a goal') but does not add significant meaning beyond what the schema provides. Baseline 3 is appropriate.

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 clearly states the tool extracts structured data from a URL without writing a schema, using an LLM to infer the schema. It distinguishes itself from sibling tools, especially extract_with_prompt, by noting it's cheaper and more consistent for similarly shaped pages.

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 provides clear context on when to use this tool (when no schema is needed, for similarly shaped pages) and mentions requirements (OpenAI-compatible LLM endpoint). It explicitly compares to extract_with_prompt but does not address other siblings like crawl, scrape, or map, nor does it state when not to use this tool.

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