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

Annotations include readOnlyHint=true (no mutation) and openWorldHint=true (may perform external calls). The description does not contradict these but adds behavioral context: it warns to wait for certificated status and artifact availability before downloading, and mentions the output format (base64 bytes). It does not disclose potential latency or external dependencies, but the annotation covers the key safety aspects.

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?

The description is concise (two sentences) and front-loads the core purpose ('Retrieve bytes only when needed') before elaborating on actions. It efficiently packs important conditions (wait for status, availability) and output format (base64) without redundancy.

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?

Given the tool's complexity (oneOf schema, multiple artifact types, dependency on other tools), the description covers the essential usage prerequisites and output. The schema is rich, so the description doesn't need to explain return values. No significant gaps identified for an agent to select and invoke this tool correctly.

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%, with detailed parameter descriptions for action, artifact, page_id, and document_id. The description reinforces key semantics (e.g., artifact options are already in schema, but description adds 'default' for original). This adds marginal value beyond the schema, hence baseline 3 is appropriate.

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 tool's purpose: downloading documents or pages. It distinguishes between artifact and page downloads, listing specific artifact types and the relationship between page downloads and find_documents. This differentiates it from sibling tools like verify or prepare.

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 guidance on when to use this tool: 'Retrieve bytes only when needed' and specifies the prerequisites for each action (wait for certificated status, use page_id from find_documents). It does not explicitly exclude alternatives, but given the tool's unique role among siblings (download vs. verify, delete, etc.), the context is sufficient.

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