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

Annotations declare openWorldHint and non-destructive read/write hints, and the description adds genuinely useful context beyond them: entitlement/gating behavior ('Free usage limits and Cue Pro entitlement are enforced by Cue'). The return summary (0-10 score, feedback, improved prompt in same language) is partly redundant with the output schema but still clarifies format expectations.

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, front-loaded with the triggering directive, followed by entitlement behavior and output description. Every sentence carries information; nothing is padded, though it is slightly dense.

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 single-parameter tool with a full schema, an output schema, and supporting annotations, the description covers trigger conditions, gating, and output shape. It is essentially complete, with only explicit non-use guidance missing.

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% for the single 'prompt' parameter, so the baseline of 3 applies. The description adds no syntax, format, or length guidance beyond what the schema already states.

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 set (review, score, refine, rewrite, improve) applied to a concrete resource (an AI prompt), so the agent knows exactly what the tool produces. The sibling get_profile operates in a different domain, so the distinction is clear without opening either schema.

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?

Explicitly directs the agent with 'Always use this tool when the user asks Cue to review, score, refine, rewrite, or improve an AI prompt,' giving concrete trigger phrases. It lacks a when-not or an alternative-routing condition, but the sole sibling is unrelated, so little is left ambiguous.

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