recommend_gifts

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds behavioral context beyond annotations: it explicitly states the tool does not compute pickup stores or travel time, and that it returns 'ideas only.' This prevents the agent from expecting logistics output. It doesn't describe return format, but the output schema exists, so that's not required. Minor gap: no mention of how candidates are ranked or whether it can return zero results, but the explicit 'ideas only' scope is valuable.

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 compact and front-loaded: the first sentence states the core purpose and scope ('ideas only'), the second sentence clarifies what it does not do, and the third gives the routing rule. Every sentence earns its place, and the most important scoping information comes first.

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 read-only, idempotent recommendation tool with 100% schema coverage and an output schema, the description is nearly complete. It covers purpose, scope, exclusions, and routing to a sibling. The only missing context is what happens when no gift candidates match (e.g., empty result behavior), but that's a minor gap given the output schema and annotations. The routing rule to plan_rush_gift is a strong contextual addition.

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 100%, so the schema already documents all 6 parameters. The description adds a high-level summary of what the parameters collectively do ('matched to relationship, occasion, budget, preferences, and constraints') but doesn't add per-parameter detail beyond the schema. Baseline 3 is appropriate because the schema does the heavy lifting and the description doesn't contradict or add significant new parameter semantics.

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 a specific verb ('Recommends gift ideas'), a resource (gift candidates), and a clear scope ('ideas only'). It explicitly distinguishes itself from plan_rush_gift by stating what it does NOT compute (pickup stores, travel time). This is a clear, specific purpose that an agent can act on.

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 description explicitly says when to use this tool vs alternatives: 'If origin, destination, or remaining minutes are available, call plan_rush_gift instead of this tool.' This is a direct, actionable routing rule. It also implies the tool is for idea generation, not logistics, which is clear context.

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