slow_ops

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

No annotations are provided, so the description carries full burden. It marks itself as a [READ] operation and explains it decodes a health check. However, it does not disclose potential side effects, required permissions, or behavior when no slow ops exist. The description is minimal but not misleading.

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 very concise: one-line summary, a usage sentence, and an Args section. It is front-loaded with the purpose and uses minimal verbiage. Every sentence adds value.

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 simplicity of the tool (one optional param, no output schema), the description is complete enough. It states the purpose, usage context, and parameter meaning. It does not explain return format, but that is reasonable for a diagnostic tool without explicit output schema.

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 only parameter 'target' is described as 'Ceph target name from config; omit for the default.' This adds meaning beyond the schema's name-only property, clarifying it's optional and comes from config. Schema coverage is 0%, so description compensates well.

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 it retrieves blocked/slow requests per OSD by decoding the SLOW_OPS health check. It specifies the resource (OSDs) and the context (clients report stalls). This distinguishes it from sibling tools like osd_perf or cluster_health.

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 explicitly says when to use: 'find the OSD sitting on blocked ops when clients report stalls.' It does not mention when not to use or list alternatives, but the context implies it's for diagnostic purposes among many Ceph monitoring tools.

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