Opt a contact out

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this is a destructive write. The description adds real value beyond that by stating the blast radius ('all texts') and the recovery path ('Only someone in the Blujay app can undo it'), which is not in any structured field. It remains silent on whether queued or scheduled messages are cancelled, whether confirmation is required, and what the call returns.

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 tight sentences with the operative effect ('Stop all texts') front-loaded, followed by the trigger and the recovery constraint. No filler and nothing important buried.

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 destructive, out-of-band-only mutation, the description covers the two most important facts (scope and irreversibility) but leaves the undocumented 'reason' parameter and the effect on pending messages unexplained. No output schema exists, so some statement about the result of the call would have helped.

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 0%, so the description carries full responsibility for parameter meaning, and it delivers almost none: contact_id is only implied and the optional 'reason' parameter is never mentioned. An agent must guess whether reason is free-text, user-facing, or required for compliance records.

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 uses a specific verb and resource ('Stop all texts to a contact'), which is unambiguous and clearly unlike any sibling such as send_message or update_group. It stops short of naming a counter-tool or contrasting scope with related operations, which is what would separate a 4 from a 5.

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?

It supplies a concrete trigger ('for example after they ask you to stop'), which tells the agent when opting out is appropriate. It offers no explicit exclusions or alternatives (e.g., when to mute rather than opt out, or what to do for a group), so usage context is clear but not complete.

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