pbi_purge_backups

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 explicitly warns that the tool is destructive, explains the dry-run behavior without 'confirm', defines the exact scope (only manifest.json directories, never loose files, symlinks, or broad roots), and states that pending journals are always preserved. This is rich, safety-critical context.

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 starts with the purpose, immediately flags destructiveness, then details safe execution and safeguards. Every sentence adds value, and there is no redundancy or wasted words.

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 description effectively covers the critical safety aspects and the dry-run return behavior (manifest). The presence of an output schema handles return value details, so the description is quite complete for a destructive tool. However, the lack of parameter explanations for 'days' and 'max_journals' is a notable gap.

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 input schema has 0% description coverage, so the description must compensate. It explicitly explains the 'confirm' parameter (dry-run when false) but does not clarify 'days', 'max_journals', or 'request_id'. This leaves most parameters undocumented and the agent guessing at their meaning.

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 starts with 'Aplica la politica de retencion a los backups' (applies retention policy to backups), which clearly states the tool's verb and resource. It distinguishes itself from sibling tools by emphasizing the destructive nature and specific scope (only journal directories), setting it apart from backup creation or recovery tools.

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 cleanup via retention policy but does not explicitly state when to use this tool versus alternatives. It provides a safety guideline (without 'confirm' it returns a manifest) but no explicit 'use when' or 'instead of' instructions, leaving the agent to infer the appropriate context.

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