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

Beyond the annotations (which already flag destructiveHint=true and readOnlyHint=false), it discloses retention limits (first 4 MiB per stream), the fact that disconnecting this tool does not stop execution, that expired output cannot be recovered by retrying, and how to interpret an unknown state with cancel_requested=true. These are exactly the operational facts an agent cannot infer from the annotations.

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?

Purpose and the start-tool relationship are front-loaded, and nearly every clause carries distinct information (retention, cancel semantics, expiry, disconnect behavior). It is dense — several clauses are packed into single sentences and the word 'previews' is left vague — but there is little outright waste.

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 7-parameter, multi-action tool with an output schema already present, the description covers what an agent needs before calling: action selection, stream/offset continuation, size retention, cancellation caveats, and irrecoverable expiry. Return-value detail is correctly left to the output schema.

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 100%, so the baseline would be 3, but the description adds real meaning: search returns up to 10 literal UTF-8 byte offsets and should be continued via next_offset, and offset is interpreted against retained output. Those semantics go beyond the enum and integer descriptions in the schema.

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?

Opens with a specific verb+resource ('Inspect a command_id from cloud_computer_command_start') and immediately scopes it against the sibling that produces the handle ('without executing again'), so an agent can tell it apart from cloud_computer_exec or cloud_computer_command_start without reading either schema.

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?

It maps each action value to a concrete intent (status polls and previews, read returns text, search finds offsets, cancel requests termination), which tells the agent which mode to pick. It stops short of explicit when-not-to-use guidance or naming alternative tools for the read/cancel split, so it is clear context rather than a full routing rule.

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