get_evidence

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

With no annotations provided, the description carries the full disclosure burden, but it only says the tool 'selectively retrieves' details. It does not explain what happens with the 'refs' list, how 'max_chars' truncates, whether the tool is purely read-only, or what a valid 'feature_id' looks like. Naming evidence types adds a little context but not enough for transparent behavioral expectations.

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 a single153 sentence with no filler, and the key idea ('selectively retrieves specific evidence details') appears upfront. It earns high marks for economy and structure, though the Korean phrasing is slightly awkward.

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 there is no output schema, no annotations, and three parameters with zero schema descriptions, the description is too thin to be a complete invocation guide. The agent knows the tool fetches evidence details from the manifest, but lacks semantics for required parameters, return format, and edge cases like max_chars truncation.

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 only partially compensates. The phrase 'specific evidence items (decision, debug, diff, commit, etc.)' hints at possible 'refs' values, and 'selectively' implies filtering, but there is no explanation of 'feature_id' or 'max_chars'. Two of the three parameters remain semantically unexplained.

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 clear verb ('가져옵니다' / retrieves) and a specific resource: detailed history of specific evidence items from the manifest, with the item types (decision, debug, diff, commit, etc.) listed. This distinguishes it from generic tools, though it does not explicitly name a sibling to differentiate from, so it stops short of a 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?

The description gives no guidance about when to use this tool versus alternatives like get_feature_manifest or get_learning_history. There is no 'use this instead when...' or 'not for...' information, so the agent must infer usage from the name and short description.

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