generate_parser

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

With no annotations, the description shoulders the full burden. It discloses the one-time LLM use, the deterministic and cost-free nature of subsequent scrapes, and the fact that selectors are verified against the page with report/coverage. It stops short of mentioning rate limits or auth, but for this read-only parser generation the core behaviors are covered.

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 sentences, no fluff. The purpose is front-loaded, followed by usage guidance and a note on verification. Every sentence contributes value and none repeat schema content.

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?

Covers the primary use pattern, the alternative, and the reliability output (report/coverage). It gives an agent enough to decide when to call and what to expect, even without an output schema. Minor gaps like conflict resolution between url and html are left to the schema descriptions, which already exist.

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 100% for all six parameters, so the schema already documents semantics. The description adds workflow context (pass parser as extract) but does not elaborate on individual parameters beyond what the schema provides. Baseline 3 applies.

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+resource: 'Look at a page ONCE with an LLM and get back CSS selectors that extract the fields you asked for.' It also clearly differentiates from ai_prompt by noting it replaces AI on repeated scrapes, making the tool's niche unmistakable.

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?

Explicitly tells when to use it: 'Use this instead of ai_prompt whenever you will scrape more than a couple of pages of the same shape.' This names the alternative and the condition that selects it, leaving no ambiguity.

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