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

Annotations already declare readOnly/openWorld/idempotent, yet the description still adds real value: per-batch caching, duplicate computation, x402 pricing on /email/intelligence/batch, and no free demo. It doesn't cover error/partial-failure behavior across a batch, which is the main residual gap.

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?

Front-loaded with the core capability, then tight labeled sections for usage and cost. Every sentence carries actionable information, including the pricing note.

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?

An output schema exists so return shape needn't be described, and bounds, dedup, caching, and cost are covered. What's missing is only the item-level format and batch failure semantics.

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?

One required parameter with 0% schema description coverage, so the description must carry the load. It compensates partially by giving the 2–25 cardinality and pointing to analyze_email's per-item schema, but it never states that items are bare email address strings or what format they take.

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 plus the batch size bounds (2–25) and the key behavioral traits (caching, dedup). It also anchors itself to the sibling by saying it uses the same per-item schema as analyze_email, so an agent can distinguish it immediately.

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?

Explicit WHEN TO CALL / WHEN NOT TO CALL sections name the alternative for single addresses (analyze_email) and the split rule for >25.

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