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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful behavioral detail beyond that: the content is returned word for word, defaults to the latest version, and the response also carries version history with per-version changes.

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?

A single dense sentence with no filler, front-loading what is returned. Minor ambiguity in 'what changed in each' (each version?), which costs a point but not readability.

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?

No output schema exists, so the description must convey return content — and it does: text plus versions plus per-version changes. Remaining gaps are small: handling of very large artifacts, non-text/binary artifacts, and the exact shape of the change records.

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 100% and the schema already documents `id` (from artifacts, e.g. a0003) and `version` (omit for latest). The description restates the version default without adding format, range, or error behavior, so it adds little over the schema — baseline 3.

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 resource and scope: the full text of ONE artifact, retrieved verbatim, optionally at a given version. That clearly separates it from the sibling `artifacts` list tool and from `evidence`/`recall`, which gather supporting material rather than a single document body.

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 only implied — you call it when you need an artifact's actual text rather than a listing. There is no explicit when-to-use/when-not, no mention of when to prefer `evidence`, `recall`, or `expand`, and no note on prerequisites (e.g. needing an id from `artifacts`).

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