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

Goes beyond the readOnly/idempotent annotations by declaring 'Runs nothing and charges nothing' — the critical safety fact for a cost-check tool. It also discloses return semantics: minimum is what the balance must cover, maximum may be replaced by a caveat, plus balance and would_402, telling the agent how to interpret an uncertain estimate.

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-loads the core purpose and the no-charge guarantee, and every clause is informative. The middle enumeration of return fields is dense and slightly run-on, but no sentence is wasted.

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?

Covers purpose, parameters, and safety for a 2-param tool with an output schema. Return fields are described even though the output schema already documents them, which is mild redundancy rather than a gap; nothing essential is 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?

With 0% schema description coverage, the description carries the burden and does so: 'operation is a tool name (fetch_url, start_crawl, research, ...) or a job operation' and 'args are that call's arguments.' Examples are concrete, though it doesn't cover edge cases like mismatched args or unknown operation names.

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 ('what a call would cost in credits before running it') and makes the pre-flight, non-executing nature unmistakable. This is clearly distinguishable from siblings like fetch_url or credits, which either execute work or report balances rather than projecting cost for an arbitrary operation.

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?

The phrase 'before running it' establishes the usage context well: call this ahead of an actual operation to check affordability. However, it doesn't explicitly rule out cases or name alternatives (e.g., when to use credits vs estimate), 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.