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

With no annotations, the description carries the full burden and does disclose real behavioral traits: an authorization restriction (admin only, never an assistant), the outbound channel behavior, and the sequencing constraint that confirmation is a separate call. It stops short of stating code expiry, rate limits, or what state changes on the line record, which keeps it out of the top band.

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?

Tight and front-loaded: the admin restriction leads, then the action, then the follow-up and the test-mode note. No sentence is wasted, though the opaque opener 'SAGOT number lines' costs a little clarity at the most-read position.

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 4-parameter mutation tool with no annotations and no output schema, the description covers the operational essentials: who may call it, how the code is delivered, and what must follow. The remaining gap is that `workspaceId` and `id` are never explained, so an agent must infer that `id` is the target line.

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% across 4 parameters. The description clarifies `channel` (SMS default, 'call' for voice) and characterizes `number` as the person's own phone, but says nothing about `id` or `workspaceId`, leaving half the parameters undocumented in both schema and prose.

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 and resource ('send a verification code to a phone number the person owns') on a number line, and explicitly distinguishes itself from the sibling it hands off to ('Then call lines.confirmNumber with the code'). An agent can identify the operation and its place in the workflow without opening any 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?

Gives explicit preconditions ('admin only (never an assistant)'), the choice of delivery mechanism with a default ('SMS (default) or a voice call'), the required follow-up step (lines.confirmNumber with the code), and a downstream condition ('Verified numbers can be called in test mode'). This is as close to a full when/how/next workflow as a description gets.

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