read

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

No annotations are provided, so the description carries the full burden. The name and content imply a non-destructive read, but it never explicitly states read-only/safe behavior, permission or auth needs, or what pagination/offset semantics apply. The offset/limit params only hint at paging behavior without explanation.

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 with the purpose, then densely encodes five action signatures with no filler. Every token carries information. It is terse to the point of being cryptic, but nothing is wasted.

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?

With 12 parameters, 5 actions, and no output schema, the description explains parameter routing but not what each mode returns (outline vs text vs format vs find) or how 'handle' ties requests to a document. For a multi-modal dispatcher this leaves real gaps about the shape of results.

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 only 25%, so the description must compensate, and it does: it maps each parameter to the action it belongs to (e.g., outline takes range/depth/offset/limit, find takes query/regex/case/whole_word/range/include_deleted/limit). That action-to-param mapping adds substantial value beyond the schema. It omits the shared 'handle' parameter, though the schema documents that one.

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 and resource (문서 읽기) and enumerates its five read modes: outline, text, node, format, find. An agent can understand the tool reads document content in multiple modes. However, it does not differentiate itself from overlapping siblings such as 'text', 'document', or 'page', which an agent might otherwise pick.

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?

No when-to-use, when-not-to-use, or alternative guidance is given. The action enumeration implies the modes exist but never says which to prefer or when to pick this tool over the sibling 'text'/'document' tools. Usage must be inferred entirely.

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