read_jar_source

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

No annotations are provided, so the description carries the full disclosure burden, and it delivers: it states the sources-JAR preference, the SNAPSHOT normal→timestamp fallback, the inner-class behavior of returning the outer class with a brief hint, the full-text return fields (class_name, artifact, source_type, code), the line-count info for segmented reads, and that failures set isError=true. This is unusually transparent for a tool with zero annotation coverage.

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 one dense, information-packed paragraph with no filler. The core purpose is front-loaded in the first sentence, and every subsequent clause earns its place (SNAPSHOT fallback, inner-class naming, line ranges, return fields, error flag). It is slightly dense, but appropriately sized for the amount of behavior it must disclose.

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 tool with 7 parameters, no annotations, and no output schema, the description covers the essentials comprehensively: source preference, fallback logic, special class-name handling, range semantics, return structure, and error signaling. The only minor gap is the absence of an explicit pointer to the sibling search tool for discovery workflows, but nothing an agent needs to call it correctly is missing.

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 57% (4 of 7 params described in schema; start_line, end_line, and prefer_sources are undocumented). The description compensates for exactly those gaps: it clarifies that start_line/end_line are 1-based and inclusive of both ends, and that prefer_sources governs the sources-JAR priority. It also adds meaning for class_name by specifying the $ inner-class syntax.

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+resource pair ('读取 Maven JAR 中指定 Java 类的源码' – read the source of a named Java class in a Maven JAR), which states exactly what the tool does. It is clearly distinguishable from the sibling search_group_id, which is a discovery tool rather than a retrieval tool, and it names the precise inputs (group_id, artifact_id, version, class_name) the agent needs.

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 rich how-to-use guidance: inner classes must use Outer$Inner, SNAPSHOT packages fall back from normal to timestamp, and start_line/end_line are 1-based inclusive ranges. However, there is no explicit when-to-use or when-not-to-use statement contrasting it with the sibling search_group_id – the differentiation is left implicit (read vs. search) rather than stated.

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