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

Goes well beyond the annotations: explains the Full Access vs scoped-grant rights model, that timeoutMs is process lifetime capped at 24 hours, that long commands return running IDs in ~2 seconds, that each call is metered as one execution, and that a returned call must not be resent. This is exactly the extra context annotations cannot convey.

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?

Front-loaded with the primary use case and the critical when-not rule, and every sentence carries information (timeouts, metering, follow-up IDs, retry rule). The sentences are long and dense, which costs a point, but there is no 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?

For a high-complexity, 9-parameter, nested-object tool with no output schema, the description covers execution lifetime, result-return modes (inline vs IDs), required identifiers, metering, and the follow-up/stop tools. Nothing an agent needs to call it correctly is missing.

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?

With schema coverage at 100% the baseline is 3, but the description adds operational meaning: timeoutMs is framed as process lifetime rather than a queue/admission timeout, operationId is a fresh UUID reusable only for retrying the identical call, and sessionId's origin is restated. deadlineAt and efficiencyProfile are left to the schema, but the required-parameter semantics are clarified.

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 command on the approved computer') and enumerates concrete command families (build, test, Git, package manager, PowerShell). It also carves out scope versus siblings by deferring host-scanning to a decline and pointing at operation_status/operation_output/operation_cancel for follow-up.

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?

Explicit trigger ('when the user asks to run a command'), explicit exclusion ('Do not use to scan or probe hosts other than this computer... decline those instead'), and named prerequisites ('Needs the sessionId from execution_session_open'). It even names the sibling tools for continuing a long-running command.

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