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

Annotations already declare destructiveHint=true and idempotentHint=true, so the agent knows this is a destructive but idempotent operation. The description adds valuable behavioral context: it returns the whole list after removal, and it returns a specific error 'recipient_not_found' when the address is not present. This goes beyond the annotations and helps the agent anticipate the outcome. It doesn't mention permissions or irreversibility, but the annotations cover the destructive nature.

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?

Two sentences with zero waste. The first sentence states the action and scope, the second states the return value and error condition. Every word earns its place. The description is front-loaded with the core behavior.

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 simple 2-parameter tool with full schema coverage and annotations covering destructive/idempotent hints, the description is nearly complete. It explains the return value (whole list) and the error case (recipient_not_found). The only minor gap is that it doesn't explicitly state that the operation is irreversible or that the recipient list is per-form, but the schema's form_id description and the annotations cover the essential context. An agent can call this tool correctly with the given information.

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%, so the schema already documents both parameters (email and form_id) with descriptions. The description adds the semantic context that 'email' is the address to remove from the recipient list, and 'form_id' is the form whose recipient list is being modified. This is consistent with the schema but doesn't add much beyond it. Baseline 3 is appropriate since the schema does the heavy lifting.

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 states a specific verb ('removes'), a specific resource ('one address from the list that receives the email on every submission'), and the scope ('keeps the others'). It clearly distinguishes this from add_recipient and other form-related tools. The title 'Remove a recipient' is also clear, and the description adds the crucial context that it's about the email notification recipient list.

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 implies when to use this tool: when you need to remove a single address from the email recipient list while preserving the rest. It doesn't explicitly name alternatives like add_recipient or say 'use add_recipient to add', but the sibling context and the phrase 'keeps the others' make the usage context clear. It doesn't explicitly state when not to use it, but the behavior is specific enough that an agent can infer the right scenario.

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