read_execution_output

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

With no annotations, the description carries behavioral disclosure. It reveals that this tool cannot circumvent the server's max_output_size and that output_truncated=true signals discarded data, providing memory-protection context. Read-only nature is conveyed by the name and verb 'Read'.

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 two-sentence description is tightly packed with no filler; it states the core operation first, then a key caveat. That caveat earns its place by preventing a false assumption about truncation.

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?

The tool likely returns output content plus a truncation flag, and enough is implied by the parameter docs and description. Since no output schema exists, a bit more explicit return-format information would make it fully complete, but nothing necessary for invoking the tool is missing.

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?

All four parameters have detailed descriptions in the schema, including defaults, ranges, encoding guidance, and how to obtain output_id. The top-level description does not add extra parameter meaning, so the baseline for 100% schema coverage applies.

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?

Description clearly says 'Read retained output from a command execution', naming the action and target resource. It does not explicitly mention sibling tools, but reading an output is distinct from listing/executing it. The 'retained output' phrase clarifies this operates on pre-existing results.

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?

There is no explicit when-to-use or alternative tool guidance. The note that output_id does not bypass max_output_size offers a boundary condition, and the output_id schema says IDs come from list_execution_outputs, but the main description leaves usage decisions mostly implicit.

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