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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description still adds real value by clarifying that nothing is auto-deleted (no cleanup side effect to worry about) and that exported data already contains these orphans, which tells the agent this is purely observational.

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?

Two short sentences, front-loaded with what is listed, then the causal explanation, then the operational caveat. No filler, and the parenthetical is doing genuine explanatory work.

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 zero-parameter, read-only listing tool this is nearly complete; the cause of orphanhood and the no-cleanup guarantee are both covered. The only gap is that no output schema exists and the description never indicates what a returned entry looks like (revision id, artifact, timestamps), which would help an agent use the result.

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 tool takes no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter claims are made or needed.

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') plus a precisely bounded resource ('artifact revisions whose pointer memory is gone'), and the parenthetical names the exact failure mode (delete on one replica racing a save on another). An agent can distinguish this from artifact_history or artifact_read purely from the definition.

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?

Usage is implied rather than stated: an agent can infer this is the diagnostic tool for inspecting orphaned revisions after a replica race. There is no explicit 'use when' clause and no naming of the sibling (artifact_history) it should be chosen over, so routing still requires inference.

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