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

With no annotations, the description carries the full burden. It does disclose the key behavioral trait — 'load=true replaces the MCP workspace (does not save)' — which warns the agent about state mutation and persistence. However, it does not say whether load=true discards current unsaved workspace content, whether the operation is reversible, or what the response contains, leaving real safety gaps.

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 sentences, purpose first, with the critical no-save caveat appended in parentheses. Every word earns its place; there is no restating of the title or redundant schema content.

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 two-parameter tool with no output schema and no annotations, the description covers purpose, rel semantics, and the load behavior, but leaves two meaningful gaps: whether load=true overwrites/discards current unsaved artifacts, and what the tool returns. The sibling version-tool family (artifacts_open_shared, artifacts_get) also argues for a one-line differentiation.

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 description coverage is 100%, so the baseline is 3 — both rel and load are already documented inline. The description adds at most the '(does not save)' nuance beyond the schema's wording, which is marginal.

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 verb-resource pair — 'Load one shared Artifacts version' — and pins down the distinguishing selection mechanism ('by relative index (-1 newest)'). This sets it apart from siblings like artifacts_list_versions (enumerates versions) and artifacts_get (current workspace), so an agent can pick it without opening schemas.

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 usage context is explicit: use this when you need to load one specific shared version by relative index, and optionally replace the workspace by setting load=true. No exclusions or alternative routing are named, but for a focused version-loader the context is clear enough.

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