uber_eats_get_preferences

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

No annotations are provided, so the description carries the behavioral burden. It discloses that this is a local-file read with no browser interaction and no login trigger, which is useful safety context for an agent. However, it doesn't describe what happens if the preferences file is missing, whether it silently defaults, or what the returned structure looks like. The 'No browser' note is genuinely valuable but incomplete on error/fallback behavior.

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 sentences, all earning their place: what it does, what it doesn't do, and when to use it. No fluff, no repetition of the tool name, and the most actionable guidance (call first, then get_address) is front-loaded in the second sentence. Exemplary conciseness.

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?

Given zero parameters, a complex web-flow context (Uber Eats with many sibling tools), and an output schema present (so return values are documented externally), the description covers the key operational facts: it's local, it's the session bootstrap call, and it avoids premature login. The main gap is that it doesn't explain how the agent should validate the returned preferences payload (e.g., what a valid response looks like), but the output schema partially handles that. Reasonably complete for its scope.

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?

There are zero parameters (100% coverage trivially), so the baseline is 4 per the rubric since no schema compensation is needed. The description appropriately focuses on behavior rather than parameters because there are no inputs to document. Nothing more is needed 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 states this reads a local preferences file containing address label and favorites defaults. It's specific about the resource (local preferences file) and distinguishes itself from sibling tools by explicitly noting 'No browser' and 'local preferences file'. However, it doesn't clearly differentiate from 'set_preference' beyond the read/write distinction, and 'preferences' is somewhat ambiguous about exactly what's contained.

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?

Excellent usage guidance: 'Call first each session' explicitly states when to use it, and it directly instructs the next step ('then get_address'). It also gives a clear when-NOT-to-use rule by advising to avoid opening login until an API tool proves the session is missing or expired. This is exemplary usage direction that references sibling tools (get_address, login) by name.

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