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

With readOnly/idempotent/non-destructive annotations already covering the safety profile, the description adds real context beyond them: bearer key requirement, no charge on hosted, error conditions (WORKSPACE_KEY_REQUIRED, NOT_FOUND, DIRECTORY_CAPABILITY_DENIED), and the non-obvious side effect that stdio may write bytes to output_path. The mention of a local byte write sits in slight tension with readOnlyHint but is about local filesystem, not server state.

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?

Front-loaded with purpose, then auth, cost, returns, and errors in a tight telegraphic style. Every clause carries signal, though the run-on single block is dense and slightly harder to scan than separated sentences.

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 annotations, an output schema, and 100% param coverage, the definition supplies the remaining essentials an agent needs: auth prerequisite, cost, error codes, and transport-dependent side effects. The only gap is that the referenced output_path is not reflected in the schema.

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 both parameters are fully documented in the schema, and the description adds little beyond it (the 'scopes the download URL' idea is already in schema). It references an output_path that does not appear in the input schema, which is more confusing than clarifying.

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 verb and resource: fetch artifact metadata (plus SHA-256 on hosted) for a succeeded job output. It distinguishes the metadata-read nature from siblings like job_status and get_receipt, though the mismatch between the tool name (download_artifact) and the 'read metadata' title leaves a slight ambiguity about whether bytes are returned or a file is fetched.

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 precondition 'for a succeeded job output' implies when this applies, but there is no explicit when-to-use/when-not and no named alternative among siblings for obtaining artifact bytes vs metadata. Usage is inferable but not spelled out.

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