read_outputs

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

With no annotations, the description carries the full burden and does so impressively: it discloses exact return representations for text, HTML, tables (first 50 rows with total), plots, images, and htmlwidgets, plus extra data such as axis ranges and ggplot2 mappings. This goes well beyond a generic 'read outputs' statement.

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 dense but well organized: it starts with the core behavior, then maps output types to return formats, then covers special metadata. Every clause adds information, though the single long sentence could be slightly easier to parse if split into structured points.

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 mixed output types and the absence of an output schema, the description does a good job explaining what callers will receive. It lacks details about app_id semantics, ids value format, ordering, or the exact contents of the 'JSON summary', but the essential behavior is clear enough for an agent to invoke 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 coverage is 0%, so the description must compensate for the schema's silence. It clarifies that an empty ids list means all outputs, which adds real meaning. However, it does not explain the app_id parameter or how ids values are structured beyond the schema's array-of-strings definition.

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 verb and resource: 'Read outputs' with an explicit scope note ('all of them when ids is empty'). It does not explicitly name sibling alternatives, but the output-focused behavior is distinct from sibling tools like get_errors, get_console, and screenshot.

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?

No when-to-use guidance is provided, and there are no explicit exclusions or comparisons to alternatives such as get_errors, get_console, or show. The intended usage is implied by the tool name and description, but the agent is not told when this tool is the right choice versus its siblings.

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