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

Annotations already declare readOnly=false, idempotent=true, destructive=false, and the description is consistent with all of them. It adds real value beyond the annotations by scoping the blast radius ('changes only this agency's playbook notes, nothing in any account') and implying idempotent re-marking via 'todo (undo a mark)'.

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 action and the three states, each with a brief inline rationale. Dense but every clause earns its place; the single sentence is slightly overloaded with parentheticals.

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 state-marking tool with no output schema, the description covers effect scope, state semantics, and non-destructiveness. Return/pagination details are unnecessary here, so an agent has what it needs to call it correctly.

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 only 50% (the two enums lack descriptions), and the description compensates by explaining the status enum values and their side effects. The step enum's members are not glossed, and note relies solely on its schema description, so it is not fully compensating.

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 (mark) and resource (playbook step for a client) and names all three states with concrete meaning. An agent can distinguish this from client_playbook (viewer) and autopilot_note without opening any schema.

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 clear when-to-use semantics for each status: skipped when the step does not apply (with a concrete ads_account example), done when finished outside Autopilot, todo to undo a mark. Lacks explicit sibling routing, but the usage context is unambiguous.

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