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

Annotations declare read-only, non-destructive and closed-world; the description adds what they cannot: identity comes from the sign-in rather than input, the returned id is opaque and stable across sign-ins, and failure mode is an error with a sign-in prompt where supported. That is substantive behavioral disclosure beyond the structured fields.

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?

Four sentences with no filler, front-loaded with the usage trigger, then return shape, then failure mode, then the explicit non-use case. Every sentence carries distinct information.

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 no-arg read tool with an output schema and full annotations, this covers purpose, invocation, return shape, error behavior and scope exclusions. Nothing an agent needs to call it correctly is missing.

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?

Zero parameters, so the schema baseline is already 4. The description further explains that no input is taken and that the account is derived from the sign-in session, which clarifies the implicit identity source, though there is little more parameter meaning to add.

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+resource ('confirm which teas.co.uk account is linked') and immediately distinguishes itself from other account tools by naming them. An agent can tell what it returns and that it takes no input without opening the schema.

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?

Explicit about when to call it ('before account tools such as my_orders, my_subscriptions or rewards_balance, or when the customer asks which account they are signed in with') and when not to ('searching, the basket and checkout work without an account'). This is routing-grade guidance covering both trigger and exclusion.

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