apply_cleanup

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

With no annotations provided, the description carries the full burden. It openly discloses destructiveness, backup creation, abort behavior without backup, the allowNoBackup escape hatch, CEP helper dependency, and result content including log and activeSequence. No relevant behavioral aspect is left unspecified.

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 long but every sentence adds value — it front-loads the destructive warning and core action, then organizes details logically (backup, abort, marker scope, requirements, side effects, result). While it could be tightened, the length is justified by the complexity of a destructive operation with multiple failure modes.

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?

Despite having no output schema, the description fully explains the return values (log array, activeSequence object) and even advises checking the backup line in the log. It covers all necessary operational context: prerequisites, failure modes, side effects, and user consent. Nothing an agent needs to call this correctly is missing.

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 already describes both parameters (mode enum and allowNoBackup with defaults), but the description adds critical context: the abort behavior when backup cannot be confirmed, the explicit condition for passing allowNoBackup, and the meaning of each mode in operational terms. This goes well beyond the schema's basic descriptions.

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 applies Lift or Extract to marker ranges with a specific prefix, and distinguishes itself from sibling selection-based tools (lift_selection, extract_selection) by operating on markers rather than selections. The verb and resource are specific and unambiguous.

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?

Provides explicit usage conditions: only acts on markers starting with 'Scout/Cleanup:', tells users to rename markers in other namespaces via remove_markers/place_markers, requires confirmation before invoking, and notes the CEP helper requirement. Clearly differentiates when to use this tool.

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