lean_profile_proof

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

Annotations already indicate readOnlyHint=true and idempotentHint=true. The description adds value by disclosing performance characteristics ('SLOW') and the specific output (per-line timing and categories). No contradictions with annotations.

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 two sentences with no extraneous information. It front-loads the core functionality and adds a critical performance warning, earning its place.

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 has an output schema and annotations, the description covers the essential aspects: purpose, output, and a usage constraint. It could be more explicit about alternative tools, but overall it is sufficiently complete for an informed agent.

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 description coverage is 100%, so each parameter is already documented. The description does not add additional meaning beyond the schema; e.g., it does not explain the relationship between parameters or provide usage examples. Baseline 3 is appropriate.

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 action ('Run `lean --profile` on a theorem') and the output ('Returns per-line timing and categories'). It distinguishes from sibling tools like lean_build or lean_verify by specifying profiling behavior.

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 warns against using the tool on theorems that already hit heartbeat limits ('SLOW - avoid...'), providing a clear when-not-to-use condition. However, it does not explicitly mention when to use this tool over alternatives like lean_verify or lean_state_search.

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