Read sandbox text file

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

Annotations already declare read-only, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new context: the 64 KiB read cap, UTF-8 encoding, the /workspace base for relative paths, and that paths target the remote sandbox rather than the MCP server. It stops short of stating truncation/error behavior on oversized or missing files.

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 short sentences with the core action front-loaded, followed by the two path caveats. No filler, and each sentence carries distinct 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 tool with no output schema and safety already covered by annotations, the description supplies the size limit, encoding, and path semantics an agent needs to call it correctly. It is slightly incomplete on large-file and missing-file behavior, but nothing critical 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?

With 50% schema coverage, sandboxId is documented in the schema and path is not. The description compensates by explaining relative-path resolution against /workspace and clarifying that paths are sandbox-relative, which is meaningfully more than the bare string schema provides.

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 ('Read ... text from a sandbox') plus scope (up to 64 KiB, UTF-8), which cleanly separates it from sandbox_write_file. It does not explicitly name or contrast with siblings like sandbox_exec, so differentiation is implied rather than stated.

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, prerequisites, or alternatives are given. It explains path resolution but never says when this tool is preferred over sandbox_exec or sandbox_write_file, leaving selection entirely to inference.

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