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 clearly describes the multi-step process (adding workspace folders, waiting for indexing, calling get_references, partitioning results) and the three-part return structure. It doesn't mention error handling, performance characteristics, or indexing timeouts, but provides substantial operational 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 appropriately sized and front-loaded with the core functionality in the first sentence. The second sentence provides important implementation details, and the third gives crucial usage guidance. Each sentence earns its place, though the middle sentence is somewhat dense with multiple operations concatenated.

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?

Given the tool's complexity (cross-repo analysis with indexing), no annotations, no output schema, and 0% schema description coverage, the description is incomplete. It explains the process and return structure well but lacks parameter documentation, error cases, performance expectations, and output format details. For a tool with 5 parameters and no structured documentation elsewhere, this leaves significant 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?

With 0% schema description coverage for 5 parameters, the description fails to compensate adequately. It mentions 'consumer_roots' and implies 'symbol_file', 'line', and 'column' through context, but doesn't explain what 'language_id' does or provide any format requirements, constraints, or examples for any parameters. The description adds minimal semantic value beyond what can be inferred from parameter names.

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 ('Find all references', 'Adds each consumer_root as a workspace folder', 'calls get_references', 'partitions results') and resources ('library symbol', 'consumer repositories', 'library_references', 'consumer_references', 'warnings'). It distinguishes from sibling tools like 'get_references' by specifying cross-repo scope and the workspace folder addition process.

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 guidance on when to use this tool: 'Use before changing a shared library API to find all downstream callers.' This gives a clear use case scenario and distinguishes it from simpler reference-finding tools like 'get_references' by indicating it's for cross-repository impact analysis.

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