uber_eats_set_preference

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

No annotations are provided, so the description carries the burden of disclosure. The description implies mutation ('Update') and shows the value format expectations (JSON string for lists/objects, plain string for scalars), which is helpful. However, it doesn't disclose whether keys are validated, what happens on unknown/invalid keys, whether setting preferences requires authentication, or what the response looks like beyond having an output schema. The mutation aspect is clear but the failure/validation behavior is not addressed.

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?

The description is reasonably concise with the core statement up front, followed by examples and Args. The examples section is the bulk of the text but earns its place by clarifying the dotted-path syntax and value formatting. The Args section slightly overlaps with the schema but adds the JSON-vs-scalar distinction not in the schema. Could be trimmed slightly but is well-structured overall.

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 this is a generic preference-setter with no enums and only 2 params, the description covers the key dimensions: path syntax, value encoding, and common use cases. The output schema exists, so return value documentation is not required. The main gaps are behavioral (validation, error handling for invalid keys) but for a low-complexity tool with good examples, this is adequate.

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 0% (the schema only provides 'Key' and 'Value' titles with no descriptions), so the description must fully compensate. The description provides rich semantic meaning: the dotted-path convention for key, the value formatting rules (JSON string for complex types), and seven concrete examples covering scalars, nested objects, lists, and currency formatting. This adds substantial value beyond the bare schema.

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 clearly states 'Update a user preference by dotted key path.' This is a specific verb+resource (update preference) with a precise mechanism (dotted key path). It distinguishes from the sibling 'get_preferences' (retrieval) and other setter tools like set_address/set_checkout_tip by targeting generic key/value preferences. It's clear but could be more distinct about how it differs from the checkout-specific set tools.

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?

The extensive examples implicitly teach when to use this tool by demonstrating the range of preference keys (default_address, default_tip_percent, dietary restrictions, budget, language). The dotted-path convention gives clear context for valid usage. However, there's no explicit 'when not to use' or alternative tool guidance (e.g., when to use set_checkout_tip instead of setting default_tip_percent).

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