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

Annotations cover readOnly and non-destructive hints, but the description adds crucial context: 'No credits spent, no I/O' clarifies it's a pure estimation with no side effects. The pricing formula (base 25, -7 for excluding ai-ugc, +3 for server render) is valuable behavioral detail not in 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?

Two tight sentences: the first states purpose and timing, the second gives the cost model and side-effect guarantee. No wasted words, front-loaded with the key distinction.

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 simple 2-param tool with an output schema, the description provides sufficient context: purpose, cost formula, and no-side-effect guarantee. The output schema presumably details the return value, so no need to explain it here.

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 coverage is 0%, so the description must compensate. It explains that 'exclude' affects cost (saving 7 credits when excluding 'ai-ugc') and that 'render' adds 3 credits, giving meaning to both parameters beyond the bare schema.

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 ('Estimate the credit cost of a snack generation') and explicitly distinguishes timing ('BEFORE running it') from the sibling generate_snacks. An agent can immediately tell this is a dry-run cost estimator.

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?

Clearly positions the tool as a pre-flight check before generation, implying when to use it versus generate_snacks. However, it doesn't explicitly name the alternative or exclusion conditions, leaving some inference to the agent.

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