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

With no annotations, the description does meaningful work: it discloses per-pair cost ($0.25), a free quota (first 10 once per operator), determinism of the scripted agent, and that scoring is blind. Those are real behavioral facts an agent would not otherwise know. Gaps remain — whether trial_id must pre-exist, whether reruns are idempotent or double-billed, and what 'score blind' yields — so the burden is only partly met.

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 with the action front-loaded and cost/quota as a secondary clause; nothing is padding. Minor cost from undefined 'pair' terminology, which is concision without clarity.

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?

A priced, mutating run against a nested-object payload with no annotations and no output schema needs more: what a 'pair' consists of, the shape of 'task', what the blind score response looks like, and whether the trial must exist first. None of that is covered.

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 0% across two required parameters, one of which ('task') is an unconstrained nested object. The description says nothing about what belongs in that object or whether trial_id references an existing trial, so it fails to compensate for the schema 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?

It states a specific verb ('Run one pair') plus the agent used ('deterministic scripted agent') and that scoring is blind, so the action is roughly identifiable. But the core resource, 'pair', is undefined jargon and nothing distinguishes this from siblings like trial_score or trial_submit_outputs, so an agent cannot tell precisely what one invocation produces.

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 description gives no when-to-use condition, no prerequisites (e.g., a trial must already be registered via trial_register_protocol), and does not name an alternative among the six sibling tools. The only usage signal is implicit pricing, which hints at frequent use but is not guidance.

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