recommend_next_actions

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

With no annotations, the description carries the full burden and does well: it discloses determinism, CPU-only execution, per-call pricing ($0.03 USDC on Base), and the key billing quirk that cost is per CALL not per habit. Missing are error behavior, latency, and whether results are cached/idempotent across identical inputs.

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 short sentences, front-loaded with what the tool returns, then cost/performance traits. No filler and no repetition of schema content.

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?

No output schema and no annotations, but the description covers purpose, return shape, determinism, cost model, and batching guidance — enough to call it correctly. A brief note on what an empty or low-confidence result looks like would close the remaining gap.

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% and the single `habits` parameter is documented field-by-field, so the baseline is 3. The batching economics are useful but already live in the schema's own description, so the tool description adds no param meaning beyond structured data.

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 output shape: 'Ranked next-best action per habit, each with a rationale and a priority score.' An agent knows exactly what it gets back. It does not, however, differentiate itself from the closest sibling build_habit_plan, leaving ambiguity about recommendations vs. a full plan.

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 cheapest endpoint, deterministic and CPU-only, so it is suitable for high-frequency loops' gives a concrete usage context (cheap, repeatable, loop-friendly) that helps an agent pick this over pricier siblings. It stops short of naming alternatives or stating when not to use it.

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