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

Beyond the readOnlyHint annotation, the description discloses truncation behavior and the explicit truncation note, the exact failure mode (unsupported_content) for binary files, and the non-obvious quirk that third-party model files prepend a full license notice as an [attribution] item. These are things an agent could not infer from the schema and would otherwise be surprised by.

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?

Three tight sentences with no filler, and the core capability plus its size cap lead the description. The attribution sentence is a bit dense but carries genuinely useful information.

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 read-only fetch with a fully described schema and no output schema, the description covers the return shape (text content, truncation note, attribution item) and the failure mode, leaving nothing an agent needs to call it 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%, so all three parameters are already documented, and the description mostly restates max_bytes and its 65536 default. It adds only the notion that truncation is reported when the cap is hit, not new semantics for run_id or path.

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 gives a concrete action and resource: 'Fetch one artifact file's TEXT content', scope-limited to a single file and capped by max_bytes. The emphasis on TEXT and 'one artifact' implicitly distinguishes it from the plural sibling mcg_fetch_artifacts, though no sibling is named outright.

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?

It clearly states when NOT to use it — binary content rejects with unsupported_content and binaries should be fetched from the run's public page — which is a real alternative path. It does not mention mcg_fetch_artifacts, so the sibling-selection guidance is implied rather than explicit.

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