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

Annotations cover the safety profile (idempotent, non-destructive), but the description adds substantial context they don't carry: the three proof mechanisms with snippets, the instant-proof email condition, the required follow-up tool, and the 401/OAuth behavior for guest calls. That is exactly the kind of behavioral disclosure structured fields cannot express.

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 tightly packed sentences, each doing distinct work: what happens, what comes back and why, and the auth/next-step constraints. Front-loaded with no filler.

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 correctly describes the return (three proof methods with exact snippets). Auth requirements, idempotent resume behavior, and the required follow-up call are all covered, leaving nothing an agent needs before invoking it.

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 100% and the single domain parameter is already documented in the schema, so baseline is 3. The description adds no formatting or normalization detail beyond what the schema provides.

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?

"Start (or resume) a claim on a tool's Atlas card for the signed-in account" gives a precise verb+resource+scope. It is clearly distinct from siblings like atlas_owner_verify (the follow-up) and atlas_owner_release (the undo).

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 agent forward ("Then call atlas_owner_verify") and states the fast path condition (verified email on the domain proves at once). It gives clear context but no explicit when-not-to-use or statement of prerequisites beyond the sign-in requirement.

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