assembly_audit_reports

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

With no annotations, the description does the heavy lifting: it discloses list ordering (최신순), that body calls return extracted PDF text, that long bodies must be continued via next_offset, that find returns offset plus surrounding context and ignores whitespace, and that one dataset is date-limited to 2001–2015. It does not cover permissions, failure behavior, or what list entries actually contain, so it is strong but not complete.

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?

Every clause carries new information and there is no filler; the parameter-driven behaviors are front-loaded in the first sentences. The prose is a dense run-on with several ideas packed into single sentences, which costs some scannability but not 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?

For a 9-parameter, no-annotation, no-output-schema tool, the description explains the two calling modes, both enums, the paging mechanism and the search helper, which is enough to call it correctly. It never describes what a list item returns (fields, IDs), leaving the agent to infer the r-/c- prefixes from the schema's doc_id note.

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%, so the baseline is 3, and the description genuinely adds meaning on top: kind's two values are explained with coverage and contents, doc_id's list-vs-body switch is stated, section=corrections is defined, and find/next_offset semantics are explained. Remaining parameters (year, query, limit, max_chars) are left entirely to the schema, so it falls short of a 5.

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 names a specific resource (국정감사 문서) and immediately splits it into two concrete modes (kind=result vs kind=correction) with the contents of each spelled out. It does not name any sibling tool (assembly_search, assembly_bill_reports, assembly_publications), so an agent cannot tell from this text alone which sibling to prefer, which keeps it at 4 rather than 5.

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?

It gives explicit mode-selection rules: call without doc_id to get a newest-first list, with doc_id to get PDF body text, use section=corrections to jump straight to the correction/action section, and use find to locate terms like member names. It also warns that correction reports only exist for 2001–2015 audits, a real usage precondition. What is missing is any comparison against alternative sibling tools for overlapping needs (e.g., general search).

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