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: it discloses return format variability ('hierarchical DocumentSymbol tree or flat SymbolInformation list depending on server support'), performance characteristics ('~5x fewer tokens than JSON'), and output optimization ('optimized for LLM consumption'). It doesn't mention error conditions or rate limits, but provides substantial behavioral context beyond basic functionality.

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 explains return variability, third provides usage context, fourth details format parameter with performance benefits. Every sentence adds value with zero waste, and key information (format option) is front-loaded in the final sentence.

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: it covers purpose, usage, behavioral traits, and parameter effects. The main gap is lack of explicit documentation for 'file_path' and 'language_id' parameters, but given the tool's relatively straightforward nature and the rich context provided, it's nearly complete.

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 3 parameters, the description compensates well: it explains the 'format' parameter's purpose and effect ('Pass format: "outline" for compact markdown output'), though it doesn't cover 'file_path' or 'language_id' semantics. The description adds meaningful value beyond the bare schema, justifying a score above the baseline.

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: 'Get all symbols defined in a document via LSP (functions, classes, variables, methods, etc.)' with specific verb ('Get'), resource ('symbols'), and mechanism ('via LSP'). It distinguishes from siblings like get_workspace_symbols (workspace-wide) and get_symbol_documentation (documentation-focused).

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 explicit usage guidance: 'Use this to get a structural overview of a file.' It distinguishes from alternatives by specifying the format parameter options ('outline' for compact markdown vs. default JSON), and implies when to use it (for file structure analysis) versus other symbol-related 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.