update_evaluator

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

With no annotations supplied, the description carries the full burden and does so: it explains versioning semantics (new source adds a version, judges use the newest from the next run, past runs keep their version), that resubmitting historical source creates no version so reverting is safe, and the server-side rejection rules around changed Metric shape/grain/range/vocabulary. This is exactly the mutation-safety context an agent needs beforehand.

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?

The description is dense and front-loaded with the operation summary before the versioning consequences, and every sentence carries operational weight. It is on the long side, and the closing 'Read the current source with get_evaluator' could have been folded into the earlier validation guidance, but there is no filler.

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 three-parameter mutation tool with no annotations and no output schema, it covers behavior, preconditions, postconditions, and return value ('The Evaluator, or an error message'). Nothing an agent needs to call this 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 compensate, and it does document all three parameters plus a constraint absent from the schema ('name ... must not be taken'). The python_code gloss stays at 'The new Python source' without format or content expectations, which is the one remaining 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?

The opening sentence names the resource (an Evaluator) and the exact operations (rename, save new source version, or both), and 'Send only what changes' makes it explicit that this is a partial update rather than a full replace. An agent can distinguish it from create_evaluator or run_evaluator without inspecting the 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?

It names concrete prerequisites and follow-ups with sibling tools: validate new code with try_evaluator first, read current source with get_evaluator, and re-check weights via list_metric_groups afterwards. It also states the failure condition (a changed declaration can break a Metric Group weight), which tells the agent when not to proceed blindly.

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