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

With annotations present, the description goes well beyond them: it discloses the API-key requirement, the idempotent semantics of an existing alert (counts only when delivery is allowed), the refusal path with an explanation, what a successful result guarantees, and a privacy detail that other channels' destination URLs are never returned. This is exactly the extra behavioral context annotations cannot carry.

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-loaded with the action and scope, then layers on constraints in roughly priority order. It is a fairly long block of prose, but each sentence carries distinct information (auth, idempotency, failure mode, return guarantee, privacy), so little is wasted.

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 everything an agent needs: credentials, what happens on the success path including the reported channel, the refusal path, and what is deliberately not returned. Nothing material is left to inference.

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's description already enumerates slug, name, product name, or custom provider, so the schema does the heavy lifting. The description restates the same source distinction without adding syntax, format, or ambiguity-resolution guidance beyond it.

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 ("starts sending the caller outage alerts for one provider") and scopes it to a single provider from either the tracked catalog or the caller's custom providers. That single-provider scope plus source distinction separates it cleanly from list/search siblings like search_providers and list_custom_providers.

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 explains what starting a watch entails and the conditions under which an existing vs. new alert is used, but it never names an alternative tool or says when a caller should watch a provider versus querying it with get_provider_status. Usage is implied by the verb rather than explicitly guided.

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