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

Discloses AI generation and caching side effects, potential inaccuracy of results, and quota/key requirements. This adds significant behavioral context beyond the annotations (openWorldHint=true), clarifying what 'open world' means in practice. No contradiction with annotations.

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 sentences: main action first, then caveats, then alternative and requirements. Every sentence adds value, no fluff, and the key differentiator is front-loaded.

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 the tool's AI-assisted behavior, quota implications, and lack of output schema, the description covers all necessary context: what it does, when to avoid it, limitations, and operational requirements. An agent has sufficient information to decide and call correctly.

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?

The schema fully describes the single parameter (word: 'English word') at 100% coverage. The description adds no extra semantic detail (e.g., format, case sensitivity, length limits) beyond the schema, so a baseline 3 is appropriate.

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 ('look up') and resource ('one English headword'), and explicitly distinguishes from sibling lookup_words by contrasting 'stored records only'. The purpose is unambiguous and differentiates well from the plural variant.

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?

Directly tells the agent when to use the alternative: 'Use lookup_words when you require stored records only.' This implies this tool is for when AI-assisted generation or non-stored records are acceptable, giving clear context for selection.

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