lean_multi_attempt

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true and idempotentHint=true, covering non-modification and idempotency. The description adds 'without modifying file' which aligns, but provides no additional behavioral details such as what the return format is or that attempts are independent. With good annotations, the description adds modest extra value.

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 a single concise sentence that covers the core action and output. It is front-loaded with the key verb 'try'. Could be slightly improved by adding a second sentence on output structure or usage context, but remains efficient.

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?

With an output schema present and good annotations, the description adequately covers the basics. The tool has 4 parameters, all documented, and no enums or nested objects. The description could mention that the output is a list of goal states corresponding to snippets, but completeness is high given the simple nature.

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?

Schema coverage is 100% with all parameters described (file_path, line, column, snippets). The description does not add any meaning beyond the schema, such as format of snippets or default behavior of column. Baseline 3 is appropriate as the schema does the heavy lifting.

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 tries multiple tactics without modifying the file and returns the goal state for each. This distinguishes it from siblings like lean_goal (single goal) and lean_run_code (modifies file). The verb 'try' and resource 'multiple tactics' are specific.

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 implies usage for testing multiple tactics but does not explicitly state when to use this tool over alternatives like lean_goal for a single tactic. No exclusions or context about when not to use it are provided.

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