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

Annotations already declare the safe read profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description's 'without changing anything' is consistent with them. It goes beyond the annotations by explaining the semantics of the universal trips@tineo.ai address and the fact that a personal address can receive mail from assistants and travel providers. It stops short of return shape/ordering specifics, so 4 rather than 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?

Front-loaded with the core action and the non-mutating constraint, with the sibling routing last. Four sentences, all carrying information; the middle sentences on the trips@tineo.ai address and assistant/travel-provider delivery are dense but earn their place for a tool whose whole value is explaining address semantics.

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 compensates by describing what comes back: the personal address when one exists, other active personal addresses, and the universal address — including the empty case. For a zero-param read tool this is everything an agent needs to call it and interpret the answer.

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 per the rubric the baseline is 4. There is nothing for the description to disambiguate, and it does not clutter itself with irrelevant parameter talk.

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 ('Read') and resource ('the authenticated user's Tineo email forwarding addresses') and immediately scopes it as non-mutating. It also enumerates the three kinds of addresses returned, so the agent knows exactly what data this tool surfaces versus the many sibling tools in the catalog.

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 names the alternative ('use forwarding_address_create') and the condition that selects it ('If the user has no personal address and wants one... after they ask for it'). This both routes the agent to the sibling and adds a consent gate, which is more than most definitions provide.

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