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

Annotations only flag destructiveHint=true; the description goes further and specifies the blast radius: alerts stop immediately, unsent alerts are dropped, but historical alerts remain in list_matches. That is exactly the consequence detail an agent needs before an irreversible call, and it is not recoverable from the structured fields.

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 short sentences ordered by importance: what it does, what happens as a result, then when to use it and the alternative. No filler and no repetition of 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 one-parameter mutation with no output schema, the description covers effect, side effects, retained state, and the sibling alternative. The only residual gap is event_id provenance, which is minor against full schema coverage.

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 100% and the single parameter carries its own description ("Event to stop watching."), so the schema does the work. The description only implies the argument via "one event" and adds no format, source, or lookup guidance (e.g. where event_id comes from).

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?

"Removes one event from the watchlist" names a specific verb, resource, and scope (exactly one entry), which cleanly separates it from watch_event (adds), list_watchlist (reads), and list_matches (history). An agent can route correctly without opening the 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?

It states the triggering condition ("when the person asks to stop watching an event") and names the alternative with the distinguishing condition ("To keep the star and turn its triggers off, use watch_event"). That is an explicit when/when-not pair, not an inference.

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