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 key behaviors: the step-by-step evaluation process, return format ('per-step diagnostics'), the safety determination logic ('identifies the safe-to-apply-through step'), and the 1-indexed position convention. However, it doesn't mention error handling, performance characteristics, or what happens with null edits.

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 perfectly front-loaded with the core purpose in the first sentence, followed by key behavioral details and usage guidance. Every sentence earns its place with no redundant information, making it highly efficient for agent comprehension.

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 complex multi-step simulation tool with 3 parameters (0% schema coverage) and no output schema, the description provides good behavioral context but leaves significant gaps. It explains the process and safety logic well but doesn't document parameter formats, error conditions, or return structure details that would be needed for reliable tool invocation.

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 fails to compensate adequately. It mentions 'edits' in the context but doesn't explain what constitutes an edit, the format of session_id, or the purpose of timeout_ms. The description adds minimal semantic value beyond what's implied by 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 ('apply a sequence of edits and evaluate after each step') and distinguishes it from siblings by mentioning its unique multi-step simulation capability. It explicitly contrasts with single-step tools like simulate_edit and simulate_edit_atomic in the sibling list.

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 find the safest partial application of a multi-step change.' This clearly indicates when to use this tool (for multi-step change safety analysis) versus alternatives like single-step simulation tools or direct application tools.

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