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

With no annotations, the description carries the behavioral burden. It discloses that only committed versions are returned, ordering is newest-first, and each version exposes sha, short_sha, date, message, tag, and commit_url. It does not address failure modes or auth effects, but for a read-style listing tool this is a modest gap.

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 front-loaded with the core verb and result, then uses a compact second sentence to enumerate version fields and the downstream fetch_design relationship. Every sentence earns its place, and the formatting of code identifiers improves scanability.

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 ties the full workflow together: design_id from roastify_list_designs, version listing here, and sha/tag refs into roastify_fetch_design. An output schema exists, so return values are otherwise covered. It omits pagination and failure behavior, but for a simple list-versions tool the essential context is present.

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 description adds little direct meaning about this tool's own parameters: npub, design_id, and dpop_token are not named. The schema already documents design_id and npub, covering 67%, and the description's useful sha/tag-to-ref guidance is cross-tool rather than input-semantic. It is adequate but not compensatory for the undocumented dpop_token.

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 opens with a specific action and resource: 'List a stored design's committed versions, newest first — the git history.' This clearly distinguishes it from list_designs and fetch_design, and the explicit sha/tag-to-ref handoff to roastify_fetch_design reinforces its role in the workflow.

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 gives practical workflow context: design_id comes from roastify_list_designs, and a returned sha/tag is used as the ref for roastify_fetch_design. This implies when to use the tool, though it stops short of explicitly stating exclusions such as 'use fetch_design when you already have the ref.'

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