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

Annotations already declare readOnly/idempotent/non-destructive/non-open-world, so the description's 'read-only' is largely redundant. It does add genuinely new behavior: the 50-item cap, newest-first ordering, the retention trigger (only on text replacement), and 'Free' (a cost trait not present in annotations).

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?

Front-loads the action and constraints ('List the earlier texts... newest first (up to 50)'), then adds only the retention rule and returned fields. Three sentences, each carrying distinct information, no padding.

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?

For a one-parameter read-only tool with no output schema, the description compensates well by naming returned fields (replaced_at, word_count, voice_match_score, full content), the item cap, ordering, and cost. Nothing needed to call it correctly is missing.

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?

Only one parameter (generation_id) and schema description coverage is 100%, so the schema already fully documents it and the description adds nothing about the parameter. Baseline 3 is correct when the schema does all the work.

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?

States a specific verb (list) and resource (a draft's earlier versions/texts) plus scope details (newest first, up to 50). This clearly distinguishes it from list_generations, though it never names the closely related sibling restore_draft_version, which is the natural counterpart for actually reverting.

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?

Gives real context on when results exist: a version is created on hand edit, paragraph rewrite, polish, humanize, AI-tell repair, or redraft. That tells the agent what history is retrievable, but there is no explicit when-not or pointer to restore_draft_version for acting on a listed version.

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