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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds nothing beyond that: it does not say whether removal is immediate or reversible, whether listing has filtering or pagination, or what happens to `label` when an item is toggled off. The parenthetical 'on=true/false' gestures at the toggle but is ambiguous about direction.

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?

A single sentence with the primary read operation front-loaded and no filler. The parenthetical mode hint is compact, though packing three operations into one clause costs some parseability.

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?

This is an overloaded read/write tool with four parameters (none required), a partially documented schema and no output schema. The description should therefore explain what a listing returns, what combination of `ref`/`typ`/`label` each mutation mode requires, and what the boolean means — none of which is 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?

Schema coverage is 50%: `ref` and `typ` are fully documented in the schema, while `on` and `label` have no descriptions. The description partially compensates by implying `on` selects add versus remove, but never states which boolean means which, and `label` is not explained anywhere at all.

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 names the resource (watchlist) and covers all three operations it performs — listing, adding and removing — plus the item types (project, company, city). The verb is overloaded across three modes, so an agent cannot tell from the name alone what calling it will do, but the description resolves that.

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?

There is no guidance on when to list versus mutate, no mention that `ref` must first come from find_projects, new_signals or my_files (that fact lives only in the schema), and no statement of preconditions for removal. The modes are enumerated but the conditions selecting them are left entirely to inference.

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