Watch a price

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

Annotations only give the generic safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds the behavior that matters: saving under an existing name replaces that watch, an observation is recorded even when history opt-in is off, and cached/rate-limited runs record nothing.

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?

It is dense and front-loaded with the core action, and parenthetical asides compress edge cases (file-unreadable behavior, cached runs) efficiently. Slightly run-on in the middle paragraphs, but no sentence is filler.

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?

An output schema exists, so return values need not be re-explained. For a stateful, side-effecting watch tool with an open-world hint, the description covers modes, persistence semantics, and recording conditions without gaps.

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 description coverage is 0% and all three params are untyped nullables, so the description carries the full burden. It does so by defining each one: name identifies the watch, kind is 'flight or hotel', and params takes 'the search_flights or search_hotels arguments', plus the semantics of omitting them entirely.

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 opening sentence names a specific verb (re-run) and resource (a saved flight or hotel search) and states the outcome (report the change). It is clearly distinguishable from siblings like search_flights and search_hotels, which it explicitly references rather than duplicates.

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?

The description enumerates each invocation mode and its effect: no arguments lists watches, name+kind+params validates/saves/runs, and name alone runs the saved search. It also supplies an explicit when-not-to-use rule ('no scheduler and no notification: do not call it in a loop').

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