inspect_class

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

With no annotations at all, the description carries the full burden of disclosing behavioral traits. It reveals that resolution can span Maven, local JARs, or the JDK, which implies potential network downloads, directory scanning, and cache writes (useCache exists in the schema), but none of these side effects are stated. The description also fails to say what happens on ambiguous resolution or what each view returns, leaving the tool's operational profile largely undisclosed.

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 two short sentences with zero waste. The core purpose is front-loaded before the view enumeration, and every word contributes meaning.

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?

For a 13-parameter tool with no annotations and no output schema, this description is too thin to be complete. It doesn't explain what each view produces, how the three resolution sources map to specific parameters, or how the tool differs from sibling tools like search_class and inspect_jar, and it cannot rely on annotations or an output schema to fill those gaps.

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 only 46% (6 of 13 parameters described), so the description must compensate. It does add meaning by enumerating the five values of the view selector and by aligning the phrase 'Maven, a local JAR, or the JDK' with the resolution-related parameters, which is helpful context. However, limit, offset, useCache, methodName, and paramTypes receive no added meaning from either the schema or the 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 opens with a specific verb pair, 'Resolve and inspect,' and a clear resource, 'a class,' then scopes it to three concrete sources: Maven, a local JAR, or the JDK. The view list (source, API, hierarchy, bytecode, all) adds functional detail that helps separate this from sibling tools like inspect_jar or scan_project at a high level. It stops short of a 5 because it never names a sibling it is not, leaving some differentiation to inference.

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 implies the tool is for inspecting a concrete class from a known source, which hints at when to use it rather than search_class or find_implementations. However, there is no explicit when-to-use guidance, no exclusions, and no mention of the alternative sibling tools, so routing is left to inference.

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