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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds real value: it discloses which metrics come back and the important caveat that runs over different markets/periods are flagged as non-comparable. That comparability handling is genuinely useful behavioral context beyond the annotations.

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 dense sentences, no filler, metrics and cardinality listed up front and the comparability caveat placed last. Every clause earns its place.

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, and the description compensates by naming the returned fields (return, buy & hold, drawdown, Sharpe, trades, win rate) and the mixed-period behavior. Complete enough to call correctly, though it says nothing about ordering or error cases (e.g., an unknown run id).

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?

With one parameter and 0% schema description coverage, the description carries the burden and does: it states the 2-6 range and that runIds may be the caller's own or public runs, adding access-scope meaning the schema does not express (the schema only encodes min/maxItems).

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?

Specific verb (compare) plus resource (saved runs/backtests), with the returned metrics enumerated and a 2-6 cardinality constraint. It is clearly distinct from single-run readers like get_run, though it never names a sibling explicitly to sharpen the contrast.

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 framing (side-by-side comparison of multiple runs) and the 2-6 constraint, but there is no explicit when-to-use vs when-not, nor a pointer to get_run for single-run inspection.

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