subgraph

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 result is raw/unprocessed ('生グラフ...そのまま返す'), includes edge types, and requires the caller to do its own traversal. These are useful behavioral cues, but it does not disclose return format details, whether the result has limitations beyond the schema's stated max radius, or any other operational 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?

Two compact sentences with zero filler. The purpose is front-loaded in the first sentence, and the second adds usage guidance that differentiates from the sibling. Each sentence earns its place, though the overall lean length trades off some behavioral depth.

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 no output schema and no annotations, the description is the only source for return expectations. It conveys that the result is a typed edge list within a radius, which is adequate for a simple two-parameter read tool. However, it omits the concrete output format and any structural details of the graph, leaving the agent to infer what 'raw graph' means in practice.

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%: both radius (default 2, max 4) and station are already documented in the input schema. The description reinforces the radius concept ('半径N駅') but adds no meaning beyond what the schema already provides. Baseline 3 is correct when the schema carries the parameter documentation burden.

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 verb+resource: it returns the raw graph (edge list with type) within radius N stations around a station. It explicitly distinguishes itself from the sibling 'neighbors' by noting it serves structural queries that neighbors cannot handle and requires self-traversal. An agent can differentiate subgraph from neighbors without opening the schema.

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 second sentence gives clear when-to-use guidance: for structural queries that neighbors doesn't suffice for, read this and traverse it yourself. It references the alternative tool and the condition that selects it. However, it does not explicitly state the inverse (e.g., 'use neighbors for simple neighbor lookups'), leaving that exclusion implied rather than stated.

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