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

Annotations are all false and offer no positive safety info, so the description carries the burden. It reveals two key behaviors: it attaches a reference without copying bytes, and private/expiring URLs are the buyer's responsibility. However, it does not disclose side effects, permission requirements, reversibility, or whether the operation mutates the project revision beyond implicit context.

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, front-loaded with the main action and key constraint, with no wasted words. The first sentence states what the tool does, and the second adds an important responsibility note. Exemplary conciseness.

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?

The description is concise and covers the tool's core distinction, but given the complexity (8 parameters, 5 required, 3 enums, 0% schema coverage), it leaves gaps: no guidance on choosing artifact_type vs. purpose, no explanation of required fields, and no detail on how checksum or filename are used. The output schema exists, so return values are covered, but the description is not fully complete for a tool with this parameter count.

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 0%, and the description does not meaningfully explain the parameters. It lists general content types ('repository, document, drawing, datasheet, BOM, or design reference') that map loosely to artifact_type or purpose, but it does not clarify required parameters (project_id, source_url, data_classification) or optional ones like checksum_sha256 or media_type. The description adds minimal semantic value beyond what the enum values already convey.

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 clearly states the action: 'Attach an HTTPS repository, document, drawing, datasheet, BOM, or design reference to the current project revision without copying its bytes.' It uses a specific verb and resource, and the phrase 'without copying its bytes' explicitly differentiates it from the sibling tool create_artifact_upload.

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 description provides clear context on when to use this tool: for referencing external content via HTTPS rather than uploading bytes. The note 'Private or expiring URLs remain the buyer's responsibility until uploaded directly' implies an alternative action (upload), but no sibling tool is explicitly named, and formal when-not conditions are absent.

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