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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered and the description is not required to restate it. It adds only a light statement of what comes back; it says nothing about rounding, currency, or how the default 15% tip behaves, which the annotations do not cover.

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?

Four short sentences, purpose stated first, then inputs, then return values — well front-loaded with no redundant prose. The list_bundles pointer is arguably filler for a tip calculator, keeping it just below top marks.

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 three-parameter read-only calculator with full schema coverage, complete annotations, and an output schema that already documents return values, the description covers purpose, inputs and usage context adequately. The remaining hole is sibling differentiation against calculate_tip_split and calculate_tip_worldwide.

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 bill, split and tip_pct are already documented with types, minimums and defaults; baseline is 3. The description paraphrases the same three inputs (“bill, tip %, people count”) but adds no format, unit, or default detail beyond the schema, and notably omits the 15% default tip.

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 and resource (“Compute restaurant tip and per-person split”) plus the three inputs, so the agent knows exactly what it produces. However, it does not distinguish itself from the near-identical siblings calculate_tip_split and calculate_tip_worldwide, which is a real ambiguity given this tool explicitly covers the per-person split case.

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?

“Use for shared meals” gives a minimal usage cue, which is better than nothing but far short of routing guidance. It points at list_bundles for related 'vie-quotidienne' calculators, which is a bundle listing tool, not a competing calculator, so an agent still cannot tell when to prefer this over calculate_tip_split or calculate_tip_worldwide.

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