osd_df

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

The readOnlyHint annotation already establishes the safe read-only nature, so the '[READ]' label is redundant. The description adds useful behavioral context about ordering (most-full first) and flags, but does not explain what the flags mean, pagination, or authentication needs.

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, and contains no filler. The purpose is stated first, followed by the only parameter's semantics, making it easy for an agent to parse quickly.

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 low-complexity, single-parameter, read-only tool with no output schema, the description provides enough context to call it correctly and understand the general return shape. It could be improved by clarifying the output flags, but the core information is present.

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?

With only one parameter and 0% schema description coverage, the description compensates well by explaining that target is a 'Ceph target name from config' and that omitting it uses the default. This adds meaningful semantics beyond the bare anyOf string/null 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?

The description states a specific read operation: per-OSD utilisation with most-full-first ordering and near/backfill-full flags. It clearly identifies the resource and metric, though it does not explicitly distinguish this from sibling tools such as osd_tree or osd_perf.

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?

There is no explicit guidance on when to use this tool versus alternatives like osd_tree or osd_perf. The '[READ]' tag and optional target hint at a safe read operation, but usage context and exclusions are absent.

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