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

Annotations declare readOnlyHint=false, which is surprising for a tool named "read"; the description reconciles this by explaining it kicks off an asynchronous background job. It further discloses the rough latency ("a minute or two") and dedupe behavior for in-flight reads, adding real value beyond the structured hints. It stops short of describing failure modes or what invalidates a run.

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?

Four tight sentences, front-loaded with the action and its async nature, then the precondition, then the follow-up. No filler and nothing buried.

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 an async job-starter with no output schema, the description supplies what an agent actually needs: it's a background kickoff, it takes time, don't re-trigger an in-flight read, and poll with compass_transformations_get. Only error/edge-case behavior is left implicit.

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%, so both parameters are already documented in the schema. The description references the PRIORITY target that maps to priorityPageId but adds no format or semantics beyond the schema, 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?

The description states a specific action ("Starts reading the five levels for a PRIORITY in the background") that is distinct from the sibling compass_transformations_get, which it names as the polling counterpart. The terminology ("five levels", "transformations") is domain-specific but the verb+resource pairing is clear enough to identify intent.

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 gives a concrete precondition ("Needs at least one kept step that impacts the priority") and explains the concurrency rule ("A read under way is left to finish"). It also names the follow-up tool explicitly, though it doesn't contrast itself against the mutation siblings like transformations_make_change.

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