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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond them: it discloses that no store or model call happens, explains the alert lifecycle (null → populated with when/price/link), and enumerates failure modes and retry policy — exactly the behavioral context an agent needs.

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-loads the core purpose and polling economy before error recovery and next steps. Dense but each sentence earns its place; the example call is slightly redundant given the schema but harmless.

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?

With no output schema, the description compensates by describing the alert payload fields (when, price, store product page link) and full error semantics, so an agent can both call and interpret the result without additional documentation.

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 100%, and the description's watch_token guidance ('use the watch_token watch_back_in_stock returned when the watch started') largely repeats the schema. The optional shopping_session_id is not addressed in the description at all. Baseline 3 is appropriate.

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 and resource ('Reads a back-in-stock watch's current state') and immediately scopes it ('from stored rows only: no store call, no model call'), which cleanly distinguishes it from siblings like watch_back_in_stock (creates) and stop_back_in_stock_watch (cancels).

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?

Explicitly says the tool is cheap to poll often, that alert is null until the store restocks, and lays out error recovery per error code (watch_not_found, rate_limited, watch_failed) plus the next-step chain (get_product, create_checkout). The agent knows when and why to call it.

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