scout_recommendations

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

Annotations already declare `readOnlyHint=true` and `destructiveHint=false`, setting a baseline. The description adds useful behavioral context: it explicitly states output is plain text only (no output-format option), which is important for parsing, and it notes the exact error behavior (does not raise on non-zero exit, but raises on missing plugin or timeout, and to inspect `raw.stderr`). This is valuable beyond annotations, but it doesn't cover all potential edge cases (e.g., what happens on network failures).

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 clear sections (main purpose, context dependency, output format, error behavior, args list, return format), but it is somewhat lengthy and could be slightly more compact. The key information is front-loaded (purpose and follow-up to `scout_cves`), and every sentence adds value, but the args list could be integrated more efficiently.

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?

The description covers the essential aspects: purpose, usage context, output format, error behavior, all parameters, and return schema. Since there is no output schema, the description appropriately details the return format. However, it could mention alternative tools beyond `scout_cves` (e.g., `scout_compare`) and provide more detail on when not to use this tool, but given the tool's complexity and absence of output schema, it is largely complete.

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%, so the description carries all parameter information burden. The description explicitly names and explains each parameter (`only_refresh`, `only_update`, `tag`, `platform`) in the Args list, adding semantic meaning (e.g., 'only show refresh recommendations (same major/minor)') that the schema properties alone lack. It does not cover `image` explicitly beyond the main purpose, but that is implied by the function. This compensates well for the lack of schema descriptions.

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 precise verb and resource ('Suggest base-image upgrades for an image') and clearly distinguishes it from `scout_cves` by positioning it as the natural follow-up when the fix is a newer base image, effectively differentiating it from its most similar sibling. This goes beyond a generic statement and gives the agent a clear purpose.

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 states the dependency on `docker login` and the `ssh://` host context, and it names the sibling tool (`scout_cves`) and the condition for use (when the fix is a newer base image). It does not fully enumerate when not to use it or compare to other `scout_*` tools (e.g., `scout_compare`), but the context is clear enough for most cases.

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