list_artifacts

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

With no annotations, the description fully discloses behavioral traits: it explains truncation behavior, that 'totalBytes' etc. count all artifacts even when rows are cut, that 'truncated' indicates subset, and that GitLab's bounded scan may cause 'jobScanTruncated' meaning totals are lower bounds. This provides comprehensive transparency.

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 punchy header, a explanatory paragraph, and a bulleted Args list. It front-loads the purpose. While arguably slightly verbose, every sentence adds value, so it is efficient for its complexity.

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 (truncation, expiry, GitLab bounded scan) and no output schema, the description provides enough detail about return fields (totalBytes, expiredButKept, etc.) and behavior. It also references a sibling tool (delete_artifacts) for context. No gaps remain for an agent to select and use it correctly.

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?

Input schema has 0% description coverage, so the description must fully explain parameters. It provides clear, concise descriptions for all three parameters: 'project' (id or path), 'limit' (max rows, default 500), and 'target' (server name, omit for default). This adds essential meaning beyond the schema's titles and types.

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 starts with '[READ] A project's artifact inventory: files, sizes, expiry', specifying a clear verb ('list'), resource ('artifacts'), and scope (inventory with file details). It distinguishes from sibling tools like delete_artifacts by stating it reports 'delete_artifacts candidates' and from other analysis tools by focusing on listing inventory.

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 states it is a read operation and gives behavior guidance: totals remain correct when truncated, and a bounded scan means totals are lower bounds. It implicitly distinguishes from delete_artifacts by mentioning candidates, but does not explicitly state when to use this vs. alternatives like artifact_storage_bloat_analysis.

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