pve_ceph_osd_tree

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

With no annotations, the description fully discloses that the tool is read-only, data is daemon-self-reported, schema has additionalProperties:1, and shape is not live-verified. It also notes that 0 is a valid OSD id.

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 detailed but well-structured: front-loaded with 'READ-ONLY', followed by structure, adversarial warning, endpoint, and expected shape. Every sentence adds value, though it could be slightly more concise.

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 presence of an output schema, the description adequately explains the tool's purpose, structure, data reliability, and edge cases (e.g., 0 as valid id). It is complete for an informed agent to use correctly.

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?

Both parameters (node, proximo_target) are well-described in the input schema. The description does not add new meaning beyond the schema, but aligns with the endpoint path. With 100% schema coverage, baseline of 3 is appropriate.

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 'READ-ONLY: the Ceph OSD list/tree — a nested CRUSH bucket structure' and provides the endpoint path. It distinguishes itself from sibling Ceph tools (like create/destroy) as a read-only operation.

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 retrieving the OSD tree and warns about adversarial data. It lacks explicit recommendations on when not to use or specific alternatives, but the read-only nature provides clear guidance.

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