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 the tool's purpose (notifying the server about external file changes), specifies change types (1=created, 2=changed, 3=deleted), and notes the required URI scheme ('file:///'). However, it doesn't mention potential side effects like server response time or error handling, leaving some behavioral aspects uncovered.

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 in three sentences: purpose, usage context, and parameter details. Each sentence adds essential information without redundancy, making it easy to parse and understand the tool's function quickly.

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 lack of annotations and output schema, the description provides strong coverage for a notification tool: it explains the purpose, usage timing, parameter semantics, and behavioral context. However, it doesn't specify what happens after notification (e.g., server response or error cases), leaving a minor gap in completeness.

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?

The input schema has 0% description coverage with one parameter ('changes'), but the description compensates by explaining that changes should include file URIs with the 'file:///' scheme and change types (1, 2, 3). This adds crucial semantic context beyond the bare schema, though it doesn't detail the array structure or null handling fully.

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 specific action ('Notify the language server that files have changed on disk') and resource ('files'), distinguishing it from sibling tools like 'open_document' or 'close_document' which handle different LSP operations. It precisely communicates the tool's role in the LSP protocol's workspace/didChangeWatchedFiles notification.

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: 'after writing files directly to disk so the server refreshes its caches.' This provides clear context for its application versus other file-related operations, and while it doesn't name specific alternatives, it distinguishes usage from tools like 'open_document' or 'run_build' by focusing on cache refresh notifications.

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