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

With no annotations, the description carries the full burden. It discloses rate limits (20 anonymous calls/24h, 100 free/key/30d), the need for an active Builder for sustained use, that guides are source-cited and 2026-accurate, and that each entry includes a canonical URL. These are concrete behavioral characteristics beyond simple existence.

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 concise—four sentences covering purpose, usage, output hint, and rate limits—with no redundant filler. It front-loads the core value proposition and then provides actionable usage and constraints.

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 listing tool with no output schema, the description provides enough to know the general scope and a key output property (canonical URL). It also covers rate limits and usage. It doesn't fully describe the return structure (e.g., fields per guide) or ordering, but given the tool's simplicity and the schema's filter coverage, this is adequate. A small gap in output structure keeps it from 5.

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?

All three parameters (limit, topic, region) have schema descriptions, so description adds little. The description's parenthetical topic list mirrors the schema enum, and 'by state' aligns with region. No additional parameter-level semantic instructions beyond schema. Baseline 3 is appropriate given 100% schema coverage.

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 identifies the tool as an index of US home-energy incentive guides by state, citing source and accuracy. It distinguishes itself from sibling tools by explicitly pointing to get_guide for full text, making its role as a listing/preview tool unambiguous.

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?

It gives explicit guidance: 'Use to ground answers about what incentives exist in a state, then fetch the full text with get_guide.' This tells the agent when to use it (to answer state-level incentive questions) and when to use an alternative (get_guide for full content). Also mentions rate limits and Builder requirement, which informs sustained use.

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