scout_recommendations

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable non-obvious behavior: it requires docker login to be useful, does not raise on non-zero CLI exit (except when scout plugin missing), and outputs plain text only. It also explicitly points to inspecting raw.stderr for errors, which is beyond annotation info.

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 moderately lengthy but well-organized: purpose statement, context, output/error behavior, and args list. Each section serves a distinct purpose and is not redundant. The args section is necessary due to 0% schema coverage. It could be tightened slightly (e.g., merging some sentences) but remains efficient.

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 tool's complexity (5 parameters, no output schema, non-trivial error handling), the description covers all essential aspects: purpose, dependencies (login), output format, error semantics, parameters, and return value structure. It even mentions the relationship to scout_cves. This is sufficient for an agent to correctly invoke and interpret results.

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 coverage is 0%, so the description must define parameters. It lists all 5 args with brief but meaningful descriptions: only_refresh and only_update explain the distinction between same major/minor and newer, tag clarifies pattern matching, platform clarifies target, and image is defined. Although not exhaustive, it compensates for the missing schema descriptions adequately.

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 the tool's purpose: 'Suggest base-image upgrades for an image.' It names the specific resource (base-image upgrades) and verb (suggest). It also distinguishes from siblings by noting it is 'The natural follow-up to scout_cves,' which shows unique positioning among the scout_* tools.

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?

Provides explicit context for when to use this tool: 'The natural follow-up to scout_cves when the fix is a newer base image.' It also notes prerequisites (docker login) and mentions the output limitation (plain text only). This gives clear guidance for selection among alternatives.

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