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

With no annotations, the description carries the full burden, and it does disclose the report's semantics: the metric is tokens spent past the verdict point, broken out by source and domain. However, it never states that this is a read-only operation, what happens when no verdict exists, or whether it errors on unknown run_ids.

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?

A single front-loaded sentence with a colon that cleanly separates the resource from its breakdown. Dense domain jargon ('verdict point', 'domain aggregate') is used without definition, which costs it the top score.

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?

With no annotations, no output schema, and an undocumented parameter, the description is the agent's only source of truth. It adequately conveys what the report contains but leaves the read-only nature, preconditions, and failure modes unstated.

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 single parameter run_id has 0% schema description coverage, so the schema adds nothing. The description only implies the parameter via 'for a run' and gives no format or lookup guidance, which does not fully compensate for the coverage gap.

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?

The description names a specific report resource (tokens spent after the verdict point) and enumerates its breakdown dimensions (per source, per domain aggregate), which is enough to distinguish it from futility_verdict or futility_judge. It stops short of explicitly naming a sibling to route against, so it lands just below the top tier.

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?

There is no statement of when to call this versus futility_verdict or futility_receipt, and no explicit prerequisites. The phrase 'after the verdict point' only implies that a verdict must already exist; the agent is left to infer the ordering and any exclusions on its own.

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