osd_mark_out

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 marks the operation [WRITE][risk=high], states it is 'Destructive to redundancy', and mentions specific risks like recovery storm and min_size. It also tells the agent how to preview safely.

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 short, front-loaded with the risk warning, and then efficiently documents each argument. Every sentence earns its place, and the format makes the safety-critical warning immediately visible.

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?

For a destructive 3-parameter tool with no output schema, the description is nearly complete: it warns of side effects, provides a preview path, and documents all arguments. It could optionally mention reversibility via osd_mark_in or how to verify completion, but nothing essential for safe invocation 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?

Schema description coverage is 0%, so the description must compensate, and it does. Each parameter gets meaningful semantics: osd_id is a numeric OSD id from osd_tree, dry_run controls preview behavior, and target names a Ceph config target with an omit-for-default default. This goes far beyond the bare type declarations.

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 opens with a specific verb and resource: 'Mark an OSD out'. It explains the operational consequence ('drains its data') and distinguishes the action from related tools like osd_mark_in or osd_purge by emphasizing the redundancy and recovery risk.

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 gives clear operational guidance — use dry_run=True to preview before committing — but it never explicitly explains when to choose this tool over siblings such as osd_mark_in or osd_reweight. The 'when to use' is implied rather than stated, and there are no exclusions or alternatives named.

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