compare_runs

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

No annotations exist, so the description carries the full burden. It discloses the central behavioral trait — reads cached results with no re-execution — which tells the agent this is a cheap, non-destructive comparison. It does not cover failure modes like mismatched metrics or invalid run_ids, but the essential behavior is disclosed.

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?

Three sentences with no filler: purpose first, then the key behavioral caveat, then a reusable invocation example. Everything 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?

For a one-parameter tool with an output schema, this is complete: purpose, behavior, and a call example are all present, and the output schema covers return values. Nothing an agent needs to invoke it correctly is missing.

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 100% with a single parameter already described as 'Two or more run_ids' with minItems 2. The description adds a concrete example with realistic 32-character hex IDs, which helps format the values, but adds no deeper semantic meaning beyond the schema.

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 and resource: compare two or more completed runs on the same metrics. The description meaningfully distinguishes from siblings like run_backtest and get_run by emphasizing it reads cached results, so an agent can tell its role without opening schemas.

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?

Implied usage is clear: use when comparing already-completed runs without the cost of re-running a backtest. The 'reads cached results, so it never re-runs a backtest' line gives the key selection context versus run_backtest, though it does not explicitly name alternatives or state when not to use it.

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