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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=false. The description adds useful behavioral context: the result is only meaningful for still-running calls and it returns what the original call would have. It does not explain polling behavior or what happens if the command completes.

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?

Efficient: the operative use case (still-running call) is front-loaded, followed by the required param and a terse list of optional controls. The trailing 'see the server instructions' is a minor deferral but not bloated.

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?

Covers the core retrieval scenario but leaves gaps: no output schema, no pagination semantics for cursor, no guidance on whether to poll or wait, and it offloads parameter detail to unspecified server instructions. Adequate but visibly incomplete for a result-fetch tool.

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%, so the description must carry parameter meaning. It explains command_id as the way to identify the pending call and briefly names response_detail, fields, and cursor, but gives no value semantics for response_detail or cursor semantics beyond a hint. Partial compensation only.

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 role: it retrieves the result of a still-running screen_* call by command_id. Distinguishes it as the companion to the async screen_* family, though it doesn't name a specific sibling to reinforce boundaries.

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?

Provides clear context: use when a prior screen_* call came back still running (awaiting user approval, or screen_record_stop still rendering). This tells the agent when to reach for it, but offers no explicit 'when-not' or direct alternative.

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