config_diff

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

With no annotations, the description carries full burden. It discloses it is a dry-run, nothing is committed, diff is credential-redacted with a redaction block, and include_secrets provides verbatim output.

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 well-structured with a bold summary, behavioral explanation, and parameter list. It is thorough but slightly verbose; could be tightened slightly.

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 no annotations and no output schema, the description covers behavioral traits and all parameters adequately. It explains the redaction block but does not detail the diff format or error handling, yet is sufficient for a preview tool.

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%, but the description provides detailed explanations for all four parameters: config_text (merge vs replace), replace (toggle), include_secrets (verbatim), and target (device name), adding significant meaning beyond the 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 clearly labels it as a [READ] DRY-RUN operation, states it stages a candidate, returns the diff, and discards it with 'Nothing is committed.' This distinguishes it from sibling tools like config_merge and config_replace.

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 explains it is the 'dry-run primitive for previewing a change' and contrasts redaction with config_backup. It implies use before committing but does not explicitly list when not to use or compare with all siblings.

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