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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuine context beyond that: the conditional nature of the payload (full report only when status is done) and the POLYRANK_API_KEY requirement. It does not cover polling cadence, report size, or behavior for an unknown/failed id.

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?

One dense sentence, front-loaded with the resource and identity, then status, then payload. Every clause carries information; the parenthetical report listing is long but each item tells the agent what to expect back.

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, describing the report sections is exactly the right compensatory move, and the status-conditional payload is important. Remaining gaps (polling behavior, failure semantics for bad ids) are modest for a simple read-by-id 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 description coverage is 0%, so the description must carry the load for the single `id` parameter. It only says 'by id', adding no format hint, no statement that it is the backtest UUID, and no note about invalid ids — the schema's uuid pattern is the sole source of that detail. Marginal compensation 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?

States a specific verb+resource ('a backtest by id') and enumerates the return payload precisely: status lifecycle (queued/running/done/failed) plus the named report sections when done. It distinguishes itself from list_backtests and run_backtest by being the single-record fetch, though it never names those siblings explicitly.

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 rather than stated — the queued/running states hint that this is the polling endpoint after run_backtest, but the agent must infer that. There is no explicit guidance on where to get the id (list_backtests / run_backtest) or what to do while status is not 'done'.

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