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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds that the call blocks until completion and yields output, but says nothing about what happens if timeout_ms elapses (error vs. partial output), which is the main behavioral risk for a blocking wait.

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?

A single well-formed sentence, front-loaded with the action and its key. Nothing is wasted, though the brevity comes partly at the cost of the missing timeout detail.

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 low-complexity 3-parameter tool with no output schema, the description covers the core contract, but it leaves the timeout parameter and the shape of 'its output' (stdout, stderr, exit status) to inference.

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 coverage is only 33% — project_id is documented in the schema while shell_id and timeout_ms have no descriptions. The description references shell_id but never explains that it comes from a prior background invocation, and timeout_ms (and its expiry semantics) is entirely unaddressed.

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 ('wait ... to finish') and resource ('background shell command') plus the keying parameter (shell_id). It implicitly distinguishes itself from the sibling `bash` tool by scoping to background commands, though it never names `bash` explicitly.

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 phrase 'background shell command' implies the workflow (start something with bash, then await it), but there is no explicit pointer to the sibling that creates shell_ids and no when-not-to-use guidance (e.g., foreground commands already return synchronously).

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