find_implementations

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

With no annotations, the description carries the full behavioral burden. It hints at behavior with 'lazy deep class metadata' but does not explain what that means in practice: filesystem access, Maven resolution, mode tradeoffs, or whether results are complete. This is too thin for a tool with no annotation safety or behavior metadata.

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 single sentence with no filler and front-loads the core action and object. The only weakness is the vague 'lazy deep class metadata' phrase, which could be clearer, but overall it is appropriately concise.

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?

This is a 10-parameter tool with no annotations and no output schema, yet the description only covers the core purpose. It omits how selectors like jarPath, coordinates, or workspacePath interact, what mode/limit/format mean, and what an agent should expect when invoking it. The description alone is not enough to call the tool confidently.

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 60%, leaving mode, limit, className, and transitive undocumented. The description partially compensates by clarifying that the tool finds direct or transitive implementations/subtypes, which implicitly documents the transitive and className parameters. However, it adds nothing for mode, limit, or selector choice.

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 uses a specific verb 'Find' and a clear resource: implementations/subtypes, with direct or transitive scoping. This sets it apart from siblings like inspect_class or search_class, though the phrase 'lazy deep class metadata' is jargon that adds little clarity.

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?

Usage is implied: use this tool when you need implementations or subtypes of a class. However, it gives no explicit when-not guidance, alternatives, or conditions for choosing this over sibling tools like inspect_class or search_class.

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