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

Going well beyond the annotations (which already mark this readOnly, idempotent, non-destructive), the description discloses the required OAuth scope (profile.read), the exact data returned, and what is deliberately excluded. It also surfaces the non-obvious host-visibility behavior around should_list_profile_preference_tools, which an agent could not infer from structured fields.

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 purpose in the first sentence, then auth/return details, which is good ordering. The closing paragraph about OpenAI/ChatGPT tools/list gating is host-implementation metadata rather than something the calling agent acts on, so it is the one piece that does not fully earn its space.

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?

Auth requirement, returned field set, and explicit exclusions are all covered, and an output schema exists so return structure need not be restated. For a zero-parameter read tool, there is no meaningful gap left for an agent to guess at.

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 no parameters, so the schema has nothing to explain and the baseline of 4 applies. The description correctly implies a no-argument call by framing this as a read of the signed-in traveler's own preferences.

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 first sentence pairs a precise verb ('Read') with a scoped resource ('the signed-in traveler's saved Sorted profile preferences'), and the body enumerates exactly which preference categories come back. This cleanly separates it from the sibling update_profile_preferences, which mutates the same resource.

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?

Usage is implied rather than stated: an agent can infer this is the read path for profile data, and the negative boundary ('Does not return chat history or account-deletion controls') helps. But it never explicitly says when to reach for this versus update_profile_preferences or which sibling to prefer for adjacent destination data.

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