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

The description does not contradict the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false); it adds meaningful behavior: updates require at least one setting to remain, calls require a Pricewatcha API key with a linked developer URL, and failures return a structured error object with specific fields. This goes well beyond the structured annotations and is genuinely useful for an agent invoking the tool.

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?

The description is compact and front-loaded: 'Update a price alert' appears first, followed by the specific behaviors, the invariant, and then auth/error details. Every sentence contributes concrete information; there is no repetition of schema field definitions or boilerplate.

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?

Given the tool has 10 parameters, a mutation operation, an output schema, and annotations, the description covers the key non-obvious aspects: allowed operation, the 'at least one setting must remain' constraint, API key authentication, and the exact error object shape. Success return behavior is not described but the presence of an output schema makes that acceptable. This is a complete update-tool description.

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?

The description adds important semantic meaning not obvious from the schema: notify_on_drop and notify_on_rise are threshold-free booleans, thresholds can be updated, and is_active can be toggled. It also clarifies that an update must leave at least one setting. With 60% schema coverage, this compensation is valuable, though a few optional parameters like webhook_url and notify_email are not described further.

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 identifies the exact action and resource: 'Update a price alert.' It then enumerates the supported mutation types — switching to threshold-free notify_on_drop/notify_on_rise, changing thresholds, and toggling is_active — which makes the tool clearly distinguishable from create_price_alert, get_price_alert, list_price_alerts, and delete_price_alert.

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 makes it clear this tool is for updating an existing alert and lists the kinds of allowed changes, so an agent can match it to an update intent. It does not explicitly name sibling tools as alternatives or state 'for creation use create_price_alert', although the constraint 'At least one setting must remain' provides a useful boundary. The context is clear enough, but not fully explicit.

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