pbi_purge_backups

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

Beyond the annotations (destructiveHint=true), the description adds substantial behavioral detail: without 'confirm' it returns a manifest without deleting; it only deletes recognizable journal directories; it never deletes loose files, symlinks, or broad roots; and it always preserves the newest journal and all pending journals. This greatly informs the agent of safety and side effects.

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 concise and well-structured: it opens with the purpose and a clear destructive warning, then details the safe behavior and retention guarantees. Each sentence adds essential operational context without fluff.

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?

The tool is destructive with 4 parameters and an output schema. The description thoroughly covers safety behavior and preservation guarantees, but omits semantics for 'days' and 'max_journals' that are necessary for an agent to use it correctly. The output schema likely covers return format, but parameter gaps make the description incomplete overall.

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 0%, so the description must compensate. It explains the 'confirm' parameter ('Sin confirm devuelve el MANIFIESTO...') but does not explain 'days', 'max_journals', or 'request_id'. These are critical for correct invocation (e.g., retention period and number of journals to keep), so the description is insufficient for parameters.

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: 'Aplica la politica de retencion a los backups' (applies retention policy to backups), and explicitly marks it as DESTRUCTIVA. This distinguishes it from sibling tools like pbi_backup_pbip_project (backup creation) and pbi_recover_from_journal (recovery), making it the deletion/retention tool.

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 does not explicitly state when to use this tool versus alternatives, nor does it name exclusions. However, the context of retention policy and the destructive hint imply it is for cleanup operations. The safety boundaries (only journal directories with manifest.json, never loose files/symlinks) provide usage constraints but not explicit alternative guidance.

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