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

Annotations already declare a safe read (readOnly, idempotent, non-destructive), yet the description adds substantial behavioral context beyond them: crash-resume without re-minting or consuming an attempt, the 60-minute expiry window, and the computed-never-stored 'expired' state from ALIP-0050 §B. This is exactly the kind of non-obvious operational detail the annotations cannot carry.

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 when-to-use clause and the key return facts, so the most important information lands first. The second half is a long, dense run-on sentence packing several conditions together, which costs some readability, but every clause carries real operational content.

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 output schema, the description must convey the return shape, and it does: per-class outlooks, scores, attempt counts, full payload for the live instance, and the next_call it instructs the agent to follow. Given the multi-state trial lifecycle (live, expired, active run), it is complete enough to call and act on correctly.

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 100% and the single optional run_id is fully documented there ('a specific run id (trn_...). Default: recent runs.'). The description never mentions run_id or adds syntax/format meaning beyond the schema, so the baseline 3 for a schema-complete tool is appropriate.

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 states a concrete resource (recent trial runs) and enumerates the payload: per-class state, scores, attempt counts, and full live-instance input plus submission instructions. It clearly separates this trial-status view from the job/delivery siblings, though it never explicitly names get_status or other lookups it must be distinguished from. A clear verb-plus-resource definition, but sibling differentiation is only implicit via the 'trial run' scope.

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?

Opens with an explicit 'When to use' clause ('Between trial submissions') and then routes the agent: follow the returned next_call while an instance is live, otherwise poll the run after expiry. It explicitly rules out the wrong calls (never finish, submit or start after expiry), leaving nothing to inference.

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