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

Annotations already declare readOnlyHint: true, so the description's statements about read behavior are not adding new behavioral transparency. However, the description adds valuable context about authorization constraints (install details returned only to buyer, email required when not signed in) that goes beyond annotations. This is borderline 5 but lacks explicit mention of what happens in error cases (e.g., wrong email).

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 sentences, each adds distinct value: first explains the output, second gives typical use cases, third explains authentication requirements. No wasted words—every sentence earns its place.

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 only 2 parameters, 100% schema coverage, no output schema, and annotations, the description is largely complete. It explains the input constraints and authorization well. Slight gap: doesn't explain what happens if an invalid order number is provided or how the agent should handle missing install details for orders that haven't shipped yet, but for a simple lookup tool this is adequate.

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% for both parameters, so baseline is 3. The description adds significant value by explaining the relationship between parameters: the 'email' is required when 'order' is a short number and customer is not signed in, which clarifies the schema's conditional requirement beyond the basic descriptions.

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 clearly states the verb ('look up'), the resource ('eSIM order'), and the specific output ('status plus SIM install details'). It distinguishes the tool from siblings like 'my_orders' by explicitly mentioning the return of install details for a single order given an order number.

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 provides explicit usage context: it's for queries like 'where is my eSIM', 'resend my QR code', or 'did my order go through'. It also gives clear when-not-to-use guidance by specifying that install details are only returned to the buyer, and explains the required pairing of short order number with email versus signed-in customers.

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