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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the bar is lower; the description still adds real substance by explaining the closed-vs-open round distinction, that closed rounds are frozen snapshots while the open round is live, and that null means 'not reported'. The GET endpoint wrapper also confirms retrieval semantics. It does not discuss pagination or volume of rounds, which is a minor gap.

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 compact sentences, front-loaded with the '[read-only]' marker and the resource, then the return contents, then provenance. No filler or restated title text; the null-convention aside is placed inline where it is most useful.

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?

No output schema exists, so the description must carry return-value meaning, and it does so well by enumerating the four things an agent will get back. What remains unstated is roughly how much data comes back per round and whether rounds are ordered — modest but real gaps for a single-call read tool.

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% and the single 'id' parameter is undocumented in the schema. The description's endpoint note (GET /api/v2/experiments/{id}/rounds) implies the id is an experiment identifier, which is genuine compensation, but it never states the expected id format or that it must be an existing experiment.

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 resource — a 'version test's rounds' — and enumerates the payload (closed-round frozen snapshots, open-round live numbers, recorded winner, repeat-winner proposal), which is far more specific than the title. It stops short of explicitly distinguishing itself from siblings like get_experiment / get_experiment_results / get_experiment_readout, so an agent must infer the difference from content rather than being told.

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?

Usage is implied by the described content (you fetch rounds when you need per-round snapshots and winner state), and the endpoint it wraps is disclosed. However, there is no explicit 'use this instead of get_experiment_readout when…' routing, and no stated prerequisites such as needing a closed round before winner data exists.

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