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 and does well by disclosing key behaviors: it returns a session ID, captures baseline diagnostics lazily on first edit per file, and emphasizes the speculative nature without committing to disk. It doesn't cover all potential behaviors like error handling or session limits, but provides substantial context beyond basic function.

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 front-loaded with the core purpose in the first sentence, followed by additional behavioral details. Every sentence adds value—explaining returns, diagnostic behavior, and usage context—with zero waste or 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?

Given the tool's complexity (creating sessions for speculative edits), no annotations, no output schema, and low schema coverage, the description is quite complete. It covers purpose, behavior, and usage well, though it could mention more about error cases or session management with siblings like 'destroy_session'.

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 schema has 0% description coverage for its 2 parameters, but the description compensates by implying their roles: 'workspace_root' likely specifies where to simulate edits, and 'language' indicates the programming language context. It doesn't detail exact formats or constraints, but adds meaningful context 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 ('create', 'simulating edits without committing') and resource ('speculative code session'), distinguishing it from siblings like 'simulate_edit' or 'commit_session'. It explains the tool creates a session for exploring changes before applying them, which is distinct from direct editing tools.

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: 'to explore what-if scenarios before applying changes'. It implies alternatives like 'apply_edit' or 'commit_session' for committing changes, providing clear context for usage without needing to list all siblings.

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