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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds real behavioral context on top: it creates an account, sends a 6-digit code to the email, requires the agent to ask the user for that code, and is only half the operation (must be completed via assistable_signup_finish). It does not state whether a half-finished signup expires or is retryable, which keeps it from a 5.

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?

The gating condition is front-loaded in the very first clause, and the four sentences cover gate, inputs, side effect/next step, and fallback with no filler. Slightly dense for a single paragraph, but every sentence is functional.

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 7-parameter mutation with no output schema, the description covers the critical unknowns: the two-step flow, the email side effect, and where to go next. Optional fields like client_name and business_name are left entirely to the schema, which is acceptable given 100% coverage, but means the description alone is not a full picture.

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 every parameter is already documented, and the description mostly restates the obvious ones (email, name). Its only added value is signaling that area_code OR city/state is the choice for the local number, but it does not say which wins if both are supplied. Baseline 3 applies when the schema carries the load.

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 ('start one [an Assistable account]') and immediately frames the scope with a negative gate: 'Only when the person has no Assistable account.' It explicitly names the sibling it is not (assistable_connect) and the follow-up tool (assistable_signup_finish), so an agent can place it in the flow 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 an explicit when-to-use condition ('no Assistable account'), an explicit when-not with the alternative ('assistable_connect is for people who have one'), and even an error branch that redirects to assistable_connect if the user reports an existing account. Nothing about tool selection is left to inference.

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