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

Annotations already provide readOnly/idempotent/non-destructive hints. The description adds behavioral value beyond those by disclosing that the body is not loaded and that no processing debit is incurred, which are meaningful operational traits an agent would not otherwise know.

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 deliver the essential information with no redundancy: what the tool does, what it avoids, and the cost implication. The key differentiator ('without loading its body') appears early.

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 low-complexity tool with rich annotations, this is nearly complete: purpose, safety, and cost behavior are all clear. The only minor gap is that the return value is not described, though no output schema exists to compensate for that.

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 0%, so the description must compensate. It does by clarifying that the artifact_id parameter refers to a stored artifact, tying the only parameter to the tool's purpose. The schema contributes the format pattern, and together they are sufficient for the single parameter.

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 uses a specific verb ('Inspect') and a clear resource ('a stored artifact'), and immediately distinguishes this tool from siblings like mithrandir_read by stating it operates 'without loading its body.' This makes its role unambiguous among the many mithrandir_* tools.

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 phrase 'without loading its body' and 'No processing debit' clearly imply this is the tool to use when only artifact metadata or status is needed and the full content/costly processing is not. It does not explicitly name alternatives or exclusions, so it stops short of a 5.

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