get_feature_manifest

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns a compressed/token-efficient representation rather than the full transcript, which is a meaningful behavioral trait. It does not discuss other side effects, limits, or authorization requirements, but the read-only verb '조회합니다' and the described output cover the main behavior.

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?

One concise, front-loaded sentence that communicates the core purpose and differentiator before any other detail. The '[MCP Tool]' prefix adds slight noise but does not undermine conciseness.

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?

There is no output schema and no annotations, and the two parameters are undocumented in both the schema and the description. The description gives a high-level idea of the return value but not the structure, parameter semantics, or how 'compressed manifest' relates to 'evidence ref list', leaving an agent short of the information needed for confident invocation.

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 0%, and the description makes no mention of feature_id or the detail enum. An agent must infer the meaning of 'quick' vs 'standard' and the format of feature_id solely from parameter names and types, with no assistance from the tool description.

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 states a specific retrieval action (조회합니다) and a precise resource: a token-efficient compressed manifest and evidence reference list rather than the full transcript. This clearly differentiates it from a full-transcript tool and from siblings like get_evidence, even though no sibling is explicitly named.

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 phrase 'instead of the full transcript' gives a clear context for when to use this tool, i.e., when a token-efficient overview is preferred. However, it does not explicitly mention alternatives from the sibling list, exclusions, or prerequisites, so usage guidance is implied rather than fully specified.

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