agm_parse_fallback

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

No annotations provided, so description bears full responsibility. It discloses that OCR requires an API key and that the tool is a fallback after AI self-correction. However, it does not mention potential side effects (e.g., network calls, time costs), nor does it explicitly state read-only or destructive nature. Adequate but not thorough.

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 well-structured with clear sections (desc, when, rule, ref) and front-loaded with the core purpose. It is somewhat verbose, mixing English and Korean, but each sentence adds value. Could be slightly more concise without losing clarity.

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?

Given the complexity of the tool (fallback with multiple parsers and tiers) and the presence of an output schema, the description provides sufficient context. It explains the interaction with XML tools and when to invoke. References to sibling tools help the agent navigate alternatives. Lacks explanation of output format differences (md vs json), but output schema may cover that.

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?

All four parameters are explained in the description, including default values and allowed options for 'parser' and 'tier'. This compensates for the 0% schema description coverage. The description adds meaning beyond the schema by listing parser choices and specifying format. However, parameter types and constraints are still left to the schema.

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 it's a fallback for when XML parsing is incomplete, using PDF/OCR. The term 'fallback' and reference to XML tools distinguish it from siblings like agm_personnel_xml. However, it lacks a succinct verb+resource phrase; the purpose is implied through context.

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 states when to use ('only when XML results are incomplete'), provides tiers with time estimates and requirements (UPSTAGE_API_KEY for OCR), and instructs AI to suggest after self-correction fails. References sibling tools for alternative approaches. Comprehensive and actionable guidance.

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