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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world. The description adds two things they do not cover: that it works signed out (no auth prerequisite) and a privacy scope note ('No contact details'). That is useful context beyond structured data, though there is no mention of the menu's format or size.

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?

Two compact sentences: triggers first, then return payload, then the signed-out and privacy caveats. Every clause carries information an agent would otherwise have to guess, and there is 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?

For a zero-parameter read-only entry-point tool with no output schema, the description covers the trigger conditions, the returned state, the auth exception, and a privacy boundary. Nothing essential for a correct first call is missing.

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?

The tool takes zero parameters, so the baseline of 4 applies. The description correctly adds no parameter discussion, and there is nothing an agent could misinterpret here.

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?

The description names concrete trigger phrases and states the payload explicitly: onboarding state (signed in or not, has a resume, has a tailored version) plus the menu. That distinguishes it from the narrower siblings like get_account and get_resume, which each return only one slice of that state. It is slightly trigger-led rather than verb-led, but an agent can still tell what it does and how it differs.

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 very concrete when-to-use signals: first open, 'what can CVEmber do', 'CVEmber, menu', 'CVEmber, help'. It also clarifies it works signed out, which is a real usage constraint. It stops short of saying when to prefer get_account or get_resume instead, so there is no explicit exclusion, but the entry-point role is clear.

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