artifact_read

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

With no annotations, the description must carry the burden of transparency. It discloses that the artifact is 'bounded' (likely by max_bytes) and supports text or image types. It does not explain behavior on exceeding the bound, authentication needs, or return structure, but the output schema partially covers returns. This is adequate but not rich.

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 a single, front-loaded sentence that conveys the core purpose, scope, and type constraints with no wasted words. It is appropriately concise for the tool's simplicity.

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?

Despite having an output schema, the description is too sparse given four parameters with no property-level descriptions. It fails to explain parameter roles, defaults, or how this tool differs from sibling read tools. The 'bounded' and 'run' context is helpful but leaves significant gaps.

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%, so the description must compensate. It does not mention run_id, relative_path, max_bytes, or project_path explicitly. 'Bounded' hints at max_bytes and 'belonging to a run' hints at run_id, but this is insufficient semantic enrichment for four parameters.

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 'Read one bounded text or image artifact belonging to a run' clearly states the verb (read), resource (artifact), scope (run), and type constraints. This distinguishes it from generic siblings like read_file or read_log.

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 'belonging to a run' implies this tool is specifically for run artifacts, giving some context. However, it does not explicitly state when to use this tool over alternatives like read_file or load_figure, nor does it mention any exclusions or limitations.

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