osd_purge

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

With no annotations, the description carries the full burden and does so: it flags '[WRITE][risk=high]', calls the operation 'Irreversible', and enumerates the exact system changes (destroy + crush rm + auth del). It also mitigates risk by offering dry_run, adding critical behavioral 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?

Compact and front-loaded: the risk marker and core action appear first, followed by dry-run and drain guidance, then a tight args list. Every sentence adds necessary information with no filler.

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 high-risk mutation with no annotations and no output schema, the description covers required state (drain before purge), preview mechanism, exact effects, irreversibility, and all parameters. Nothing needed to call it safely 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 coverage is 0%, so the description must explain each parameter, and it does: osd_id is a numeric OSD id from osd_tree, dry_run controls preview vs actual purge, and target is an optional Ceph target from config with default behavior. The value goes well beyond the bare schema.

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?

States a specific verb and resource: 'Purge an OSD', and lists the exact destructive steps ('destroy + crush rm + auth del'), making the operation unambiguous. It is clearly distinct from sibling tools like osd_mark_in/osd_mark_out and osd_reweight, which are non-destructive lifecycle operations.

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?

Gives explicit operational guidance: 'Pass dry_run=True to preview' and 'Drain first (osd_reweight 0 → mark out → wait active+clean) before purging'. This tells the agent the safe invocation flow and prerequisites, which is more than most sibling definitions provide.

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