submit_experiment

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

No annotations are provided, so the description carries the full burden. It discloses two genuine behavioral traits beyond the schema: submission is queued rather than executed inline, and identical request IDs are idempotent. It omits other important behavior — what happens when the budget is exceeded (error vs. truncation), whether validation failures reject the request synchronously, and how to follow the queued work via get_run/list_runs.

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?

A single front-loaded sentence with no filler, and the most decision-relevant fact (idempotency) is placed where it will be read. It is efficient, though the extreme economy leaves no room for the routing or budget semantics the tool needs.

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?

Given a 2-parameter tool whose main parameter is a deeply structured experiment specification, zero schema coverage, and no annotations, one sentence is far short of what an agent needs to construct a valid submission or predict failure modes. The existence of an output schema excuses it from describing return values, but not from explaining the spec's core blocks or the queue lifecycle.

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%, and the schema is a very large nested ExperimentSpec with dozens of undocumented fields (program operations, captures, weight reads, generation, diagnostics). The description only adds meaning for request_id via the idempotency clause and hints at budget via "bounded"; it explains nothing about how spec is interpreted.

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 ("Queue ... experiment") and adds a scoping qualifier ("bounded") that signals budget-limited submission. It does not distinguish this from the near-identical sibling submit_inspection, which also submits an ExperimentSpec-shaped payload, so the agent cannot tell them apart from the description alone.

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?

The idempotency clause implicitly tells the agent to reuse a request_id for safe retries, which is real usage guidance. However, there is no statement of when to choose this tool over submit_inspection or submit_study_candidate, and no prerequisites or exclusions are given.

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