try_evaluator

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

No annotations are provided, so the description carries the full burden and does so well: it discloses the side-effect profile ("Persists nothing"), the cost model (a model call per judged turn on the customer's provider), the semantics of each outcome value (ERRORED → read error_detail; RUNNING → poll get_evaluation_try), and the shape of the result (metrics with rationales, trace_summary).

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-loaded with the core action and the no-persistence guarantee, then layers usage, cost, and outcome semantics efficiently. The trailing ":param"/":returns:" epilogue partially restates content already given in prose, a minor redundancy.

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 4-parameter, no-annotation, no-output-schema tool, the description supplies everything an agent needs: purpose, usage, cost, failure handling, polling behavior, and the meaning of each returned field. Nothing material 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 description coverage is 0%, so the description must compensate, and it documents all four parameters in prose, adding real meaning beyond the bare schema: session_id is a search_session_id or a single-turn run's query_id, and wait_seconds controls how long before handing back the id to poll. It stops short of format details but fully closes 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 and resource ("Tries Evaluator source on one Session") plus a scope constraint ("Persists nothing"), which immediately separates it from siblings like get_evaluation_try, get_evaluator, and list_evaluators. The agent knows exactly what operation this performs before opening any schema.

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?

Gives explicit use cases ("check a draft before showing it as ready", "judge a replayed Session against its source") and routes to alternatives (read a version's python_code with get_evaluator to try a saved Evaluator). The condition selecting this versus get_evaluation_try is also spelled out via the RUNNING/poll flow.

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