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 excels by explicitly stating the destructive nature, the dry-run safety behavior, the exact types of directories deleted (with manifest.json), and the preservation of recent and pending journals. It also mentions exclusions like loose files, symlinks, and broad roots. This is exemplary transparency.

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 three sentences long and efficiently front-loaded with the core purpose and destructive warning. Every sentence adds value: purpose, dry-run behavior, and safety constraints. There is no fluff or repetition, achieving maximum signal density.

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 is destructive and has an output schema, the description covers the essential context: what is deleted, what is preserved, and how to preview via dry-run. It is complete enough for an agent to invoke safely. However, it does not detail the output manifest structure or the exact role of all parameters, though the output schema partially compensates for the former.

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 has 0% description coverage, so the description must compensate. It directly explains the 'confirm' parameter (dry-run vs. actual deletion) and implies the purposes of 'days' and 'max_journals' through the concept of retention policy. However, it does not explain 'request_id' nor the precise interaction between 'days' and 'max_journals', leaving some parameter semantics unclear.

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 retention policy to backups' and marks itself as 'DESTRUCTIVE'. It specifies the resource (backup journal directories) and the action (purge/delete), distinguishing it from sibling tools like pbi_backup_pbip_project (creating backups) and pbi_inspect_journal (inspecting journals). The scope is 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?

The description provides clear context for when to use the tool: applying retention policies to clean up old backups. It also gives important usage guidance by explaining the dry-run mode without 'confirm' and the constraints on what is deleted. However, it does not explicitly name alternative tools or say when not to use it, so it falls short of a 5.

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