exec

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that: it discloses exactly what is returned on fast completion (stdout/stderr plus exit code in the same call) and that a slow command silently converts into a persistent session returning a sessionId. It omits timeout/cancellation behavior and permission requirements, keeping it from a 5.

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?

Two tight sentences, front-loaded with the core action and followed by the conditional outcome, with no redundancy. The adverb 'efficiently' is mild filler that earns nothing, otherwise the structure is exemplary.

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 session-spawning shell tool with no output schema and zero parameter documentation, the description covers the most important unknown (what comes back and when it becomes a session) but leaves four of five parameters, timeout behavior, and session lifecycle unaddressed. Adequate but with clear gaps.

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 0% across 5 parameters, so the description carries the full burden and mostly fails it. It explains only detachAfterMs (indirectly, via the completion threshold) and the command parameter; cwd, shell, and timeoutMs are never mentioned, leaving the agent to guess their semantics and defaults.

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+resource ('Run a shell command') and the description's second sentence clarifies the execution model. However, it never distinguishes itself from the sibling process_start, which an agent could reasonably pick for the same task, so it falls short of a 5.

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?

Usage is implied rather than stated: nothing says when to use exec versus process_start, process_read, or process_input. The description does explain the conditional fallback to a persistent session, which hints at how the tool behaves, but there are no explicit when/when-not rules or named alternatives.

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