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

Annotations already declare readOnlyHint=true and destructiveHint=false, so "Read-only" is largely redundant. However, the description adds genuine behavioral context beyond the annotations: expected timing ("usually under a minute"), polling cadence, and the meaning of transitional states.

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?

Three sentences, front-loaded with what is returned, then the polling lifecycle, then state interpretation. No filler; every clause carries operational meaning.

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?

An output schema exists, so return structure needn't be re-explained, yet the description still orients the agent on which fields matter (state, cleanup_confirmed). Combined with read-only annotations and clear polling guidance, nothing needed to invoke this 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?

Schema description coverage is 100% and the single session_id parameter is fully documented in the schema with pattern and origin (returned by start_mac or list_mac_sessions). The description adds no syntax or format detail beyond that, so the baseline 3 applies.

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 and resource ("Read one Mac session") and enumerates exactly what it returns: state, funded time, cost so far, cleanup confirmation. It is clearly distinguishable from list_mac_sessions and read_mac_output among the siblings.

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?

Gives explicit when/when-not routing: poll after start_mac until state is ready, poll after stop_mac until cleanup_confirmed is true. It also decodes intermediate states (queued/provisioning = wait; stopping is not yet confirmed cleanup), so the agent knows how to interpret responses without guessing.

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