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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that the effect is on editor display state, but it does not say whether the review marking is reversible or persistent across sessions, which matters for a state-mutating tool.

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?

Two short sentences with zero waste; the behavioral effect comes first and the usage restriction follows. Nothing is padded or repeated from the title.

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 3-parameter mutation with no output schema, the description covers purpose and invocation policy well but leaves the 'all' parameter and the reversibility of the review marking unexplained. An agent can call it correctly in the common case but may guess wrong on bulk review.

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 67%, with 'steps' and 'projectId' documented in the schema itself. The description adds no parameter meaning and never explains the 'all' boolean, which is undocumented in both places and is the most consequential parameter here.

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 ('Mark steps as reviewed') and the concrete effect ('stop showing as your changes in the editor'), which is more than a restatement of the name. It does not explicitly contrast with close siblings like revert_changes or list_changes, so the differentiation is only implicit.

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 unusually explicit when-to-use guidance: 'Only when the user asks: reviewing your work is theirs to do' tells the agent not to invoke this proactively. It stops short of naming alternatives (e.g. revert_changes for undoing rather than accepting), so 5 is not warranted.

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