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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that shell state (cd, env vars, aliases) persists across calls and that commands are limited to 30s, both non-obvious traits. However, it does not mention whether a session must be established first via huaweicloud_sandbox_connect, nor what the response format is—minor gaps given the richness of what is stated.

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 sentences with zero fluff. The primary purpose and key distinguishing trait (session reuse) are front-loaded, followed by usage guidance and a clear exclusion with the preferred alternative. Every sentence earns its place.

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 no output schema and no annotations, the description covers the essential decision factors (session reuse, 30s limit, alternative tool). It does not explicitly mention prerequisites like establishing a session via huaweicloud_sandbox_connect or the return value format, but these are implied by the sibling set and the tool's nature. A small but acceptable gap for an experienced agent.

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 the schema already documents all four parameters. The description adds no syntax or format details beyond the schema, staying at the baseline for parameter semantics. It does not clarify the relationship between workspace_id and the HW_WORKSPACE_ID environment variable beyond the schema's note.

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 states a clear verb ('Execute a command') and resource ('workspace terminal') with an explicit qualifier ('with session reuse'), immediately distinguishing it from the sibling exec_one_shot by highlighting state persistence. It also names the alternative in the exclusion clause, leaving no ambiguity about what this tool does.

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?

Explicit guidance is provided: 'Use for interactive work and command sequences that need shared state' and 'NOT for long-running commands (>30s) — prefer exec_one_shot for those.' This gives clear when-to-use and when-not-to-use criteria, directly referencing the relevant sibling.

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