agent-lsp

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

With no annotations provided, the description carries full burden and does well by disclosing: 1) the specific command execution patterns for different languages, 2) that test failure locations are LSP-normalized for use with go_to_definition, 3) the exact return structure, and 4) that it doesn't require start_lsp. It doesn't mention error handling, timeout behavior, or permission requirements, but provides substantial operational 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: first sentence states core purpose, second provides language-specific implementations, third explains optional parameter, fourth describes output normalization, fifth specifies return format, sixth clarifies LSP dependency. Every sentence adds value with zero redundancy.

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 3 parameters, 0% schema coverage, no annotations, and no output schema, the description does well by explaining the execution behavior, return format, and LSP integration. It could better explain all parameters and error cases, but provides substantial context for a testing tool in this environment.

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 0%, so the description must compensate. It mentions 'Optional path param narrows scope' which explains one parameter, and implies language detection from workspace context, but doesn't explain workspace_dir or language parameters. With 3 parameters and only 1 partially explained, this meets the baseline for incomplete coverage.

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: 'Run the test suite for the detected workspace language' with specific implementation details for different languages (go test, cargo test, pytest, npm test). It distinguishes itself from siblings like 'get_tests_for_file' (which retrieves tests) and 'run_build' (which builds rather than tests).

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 provides clear context about when to use it: for running test suites in various programming languages. It mentions an optional path parameter to narrow scope and explicitly states 'Does not require start_lsp', which helps differentiate from LSP-related tools. However, it doesn't explicitly state when NOT to use it or name specific alternatives among siblings.

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