agent-lsp

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes what the tool does (analyzes symbol references and partitions callers), what it returns (three specific data structures), and operational context (use before editing). It doesn't mention performance characteristics, rate limits, or authentication needs, but provides substantial behavioral context.

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 efficiently structured with three sentences: the first explains the core functionality, the second specifies the return structure, and the third provides usage guidance and parameter semantics. Every sentence adds value with zero wasted 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?

For a tool with no annotations, no output schema, and 0% schema description coverage, the description provides excellent context about functionality, usage, and parameters. It doesn't specify exact return formats or error conditions, but gives sufficient information for effective tool selection and invocation given the complexity.

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?

With 0% schema description coverage for both parameters, the description fully compensates by explaining both parameters: 'changed_files' is implied through context ('specified files'), and 'include_transitive' is explicitly described with its effect ('surface second-order callers'). The description adds essential meaning beyond the bare schema.

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's purpose with specific verbs ('enumerate', 'resolve', 'partition') and resources ('exported symbols', 'callers', 'test vs non-test'). It distinguishes itself from sibling tools by focusing on change impact analysis rather than general code navigation or editing functions.

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 states when to use this tool ('Use before editing a file to understand blast radius') and provides guidance on parameter usage ('Set include_transitive=true to surface second-order callers'). It clearly differentiates this from editing or navigation tools in the sibling list.

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