get_source

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

With no annotations, the description must fully disclose behavior. It mentions the operation is 'expensive' but fails to explain error handling, rate limits, or what happens if the node does not exist. The return format is not described, leaving significant gaps for an agent.

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 extremely concise: two short sentences convey purpose, usage guidance, and parameter hints. No unnecessary words.

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 the complexity (2 params, no output schema), the description covers purpose and parameter usage but omits the return value structure, error scenarios, and prerequisites. It is adequate but not complete.

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 descriptions are missing (0% coverage), so the description adds meaning by explaining the difference between `id` and `ids`. However, it implies these are mutually exclusive ('for one' vs 'for several'), which the schema does not enforce, potentially misleading an agent.

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 clearly states the tool retrieves 'raw source' for a node, contrasting with `locate` which provides a snippet. However, it does not define what 'source' means in this context (e.g., code text), and only differentiates from one sibling, leaving ambiguity with other siblings like `get_context`.

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 explicitly says `locate` already includes a snippet, so this tool is often unnecessary, providing direct when-to-use guidance. It also labels the operation as 'expensive', implying careful use. However, it does not address alternatives like `search` or `get_context` for similar purposes.

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