session_exec

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

With no annotations provided, the description carries full burden. It states that the session is 'temporary' and 'automatically cleaned up after execution,' which tells the agent the session has a short lifecycle. However, it omits important behaviors: what happens on timeout (partial output vs. error), how truncation affects returned data, whether state is preserved between executions, or that cleanup means the session cannot be reused. Given zero annotations, more behavioral context is expected.

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 consists of two sentences, totaling 20 words. It immediately states the core action and outcome, then adds one critical piece of lifecycle information. Every word earns its place with no redundancy or filler.

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 complexity (6 parameters including enums, no output schema), the description is too sparse. An agent needs to know: what happens on timeout, the format of returned output, whether stderr is captured, and how truncation modes differ. Since there is no output schema, the description should compensate by summarizing return behavior.

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 each parameter already has a description in the schema. The tool description adds no additional semantic context beyond what the schema provides. The baseline of 3 is appropriate because the description does not explain how parameters interact (e.g., how truncation modes affect output, or that cols/rows are only meaningful for interactive programs).

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 'Execute a command in a temporary session and return the output,' which specifies the action (execute), the resource (temporary session), and the result (return output). This differentiates it from sibling tools like session_send (which sends input without returning final output) and session_read (which reads existing output). The addition of 'temporary' and 'automatically cleaned up' adds valuable distinction.

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 description provides no guidance on when to use this tool versus alternatives like session_interact, session_send, or session_read. It doesn't explain that this is a one-shot execution tool suitable for quick commands, while session_interact is for ongoing interaction. No prerequisites, when-not-to-use, or behavior for long-running commands is mentioned.

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