update_test_case

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

With no annotations, the description carries the full burden and does most of it: it discloses merge-not-replace semantics, that ``inputs`` and ``expected`` replace rather than merge, that ``clear`` removes fields, and that the call returns the test case or an error. Gaps remain around permissions and side effects on stored experiment replays.

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 two facts an agent needs (what it changes, and that omitted fields are kept), then a compact per-parameter list. The Sphinx-style ``:param:`` formatting is a little mechanical but each line carries distinct information.

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?

An 8-parameter mutation tool with no annotations and no output schema needs strong prose, and this supplies semantics, a constraint, and a return description. It could say more about error cases and access requirements, but nothing essential for calling the tool 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 description coverage is 0%, so the description must document all 8 parameters and it does: it explains the id params, the ``{name: value}`` shape of ``inputs``, that setup/cleanup are Python source run before/after every replay, and that ``clear`` removes fields. This adds meaning well beyond bare property names.

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?

"Changes one test case of a Dataset" gives a specific verb and resource, and "one test case" separates it from batch siblings like add_test_cases, remove_test_cases and copy_test_cases. It does not name any sibling explicitly as an alternative, so it stops short of full differentiation.

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 description establishes the partial-update model ("Fields you leave out are kept") and an explicit precondition/exclusion: ``inputs`` works only on a test case created with ``inputs``, not a Session-based one. That is real when-to-use guidance, though it never names an alternative tool for the Session-based case.

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