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

Adds substantial behavior beyond the annotations: ownership requirement ('the list must be yours'), recipient must be org-known, burst limits, SMS quota, STOP opt-outs, and that the list link is auto-appended. Annotations only give safety hints, so this guard-level detail is genuinely valuable context an agent cannot infer.

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?

Front-loads the verb and resource, then packs constraints efficiently. The guard enumeration reads as one long run-on clause, slightly dense, but nearly every element adds actionable 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 non-idempotent, open-world mutation with no output schema, the description covers recipients, guards, quota/opt-out rules, parameter constraints, and the sibling alternative. An agent has everything needed to call it correctly.

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?

With 0% schema coverage the description carries the load and does so well: it documents the worker_id/phone mutual-exclusivity ('one') and the 300-character cap on message, both constraints absent from the schema. Minor gap on phone format syntax keeps it from 5.

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 ('Nudge'), resource ('a worker'), channel ('by text') and object ('about a task list'), plus the underlying endpoint. It distinguishes itself from the sibling tascan_send_sms by naming it as the 'general text lane', so an agent can tell which of the two to pick.

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?

Explicitly routes the general case to tascan_send_sms and implies this is the list-specific lane, and it states the delivery-identifier choice (worker_id OR phone, one). It lacks an explicit 'do not use when' beyond that sibling pointer, keeping it at 4 rather than 5.

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