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

Annotations only supply destructiveHint=true; the description adds substantive context beyond that: the 'WRITE:' classification, the fact that no SMS is sent, and the important consequence that rejoin is only possible via SMS. It does not cover idempotency or behaviour when the contact is unknown, but the key side effects are disclosed.

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 short sentences, front-loaded with the 'WRITE:' classification and the primary effect, with no filler. The trailing 'FireText: /unsubscribe.' endpoint note is minor but provides API mapping value.

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 3-parameter destructive write with minimal annotations and no output schema, the description covers the critical points: scope default, no SMS sent, and irreversibility without SMS. Only the response shape and not-found behaviour are left unspecified.

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 coverage is 100%, so baseline is 3, and the description adds real meaning beyond the schema by clarifying that omitting 'group' unsubscribes from all groups (the schema only says 'only if the account unsubscribes per group'). The mobile and subaccount params remain schema-documented only.

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 (opts out) plus resource (a contact in the FireText account) and the effect (no longer receives group messages). The default scope ('all groups') and the contrast with the sibling firetext_subscribe_contact make the operation unambiguous.

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?

Gives clear context for use: default is account-wide opt-out, with the group parameter only applying when the account unsubscribes per group. It does not explicitly name firetext_subscribe_contact as the inverse or state exclusions, but the conditions for using the default vs per-group mode are spelled out.

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