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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, and the description adds information annotations cannot: it is staff-only and it surfaces failure state and login-sent status. It goes beyond the safety profile without contradicting it.

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 audience restriction is front-loaded, followed by one dense sentence on what the tool reveals and one on why to call it first. No filler, and the ordering matches how an agent reads it.

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?

There is no output schema, so the description carries the return-value burden and largely does so by naming progress, prior actions, errors, and login status. Combined with full annotation coverage for a read-only tool, only the ambiguity against get_onboarding_status keeps it from being complete.

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?

Single parameter with 100% schema description coverage, so the schema already defines the email argument. The description adds no syntax, format, or matching behavior for the lookup key, leaving the baseline of 3.

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 (customer onboarding progress), enumerates what it returns (progress, actions taken, failures, login sent), and flags the audience restriction. It never distinguishes itself from the near-identical sibling get_onboarding_status, so an agent choosing between the two gets no help.

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 sequencing guidance: look at this before send_customer_welcome, with a concrete rationale (the research step can misread a site, cheaper to catch before the customer is contacted). It does not address when-not-to-use this versus get_onboarding_status, so the guidance is directional but incomplete.

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