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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds real context beyond them: a hard cap of 30 keywords on a project, priority ordering in sweeps, and the restore path from remove_keyword. It stops short of covering duplicate handling or how the 'confirm' guard interacts with adding.

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 tight sentences, front-loaded with the core action, followed by behavioral detail and the undo routing. No filler, though the undo sentence could be trimmed without losing 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?

For a 4-param mutation tool with no output schema and annotations covering safety, the description supplies the missing behavioral facts (cap, sweep priority, undo path). Gaps remain around duplicate keywords and the confirm-guard flow, but the essentials for correct invocation are present.

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 75% schema coverage the schema carries most of the load, but the description adds genuinely new meaning: the 30-keyword cap constrains the required keyword parameter, and it explains that the nested restore object replays remove_keyword's undo (position plus whether it was custom) — details the schema descriptions don't fully spell out.

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: tracking a search keyword on a project. The limit (30 at most) and the routing note to remove_keyword's undo.restore help distinguish it from list_keywords/remove_keyword, though it doesn't explicitly name those siblings as alternatives.

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 one concrete usage rule — pass undo.restore to reverse remove_keyword — and implies the tool's role ('searched first by every sweep'). But it never states when to add a keyword versus using add_suggested_competitor or list_keywords, and gives no prerequisites beyond the implicit 30-keyword cap.

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