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

Annotations already carry readOnlyHint=false, destructiveHint=true, and idempotentHint=true, so the safety profile is known. The description adds meaningful behavior beyond that: it clarifies that the draft is mutable while published versions are immutable, and that runs pinned to published versions keep working. This addresses a key state-change consequence that annotations alone do not convey.

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?

Two sentences deliver the core action, scope, a documentation pointer, and an important immutability caveat. The key facts are front-loaded ('Update an extractor's mutable draft...'), and there is no filler or repetition of schema contents. The parenthetical about get_documentation is slightly interruptive but earns its place by preventing a common mistake.

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 5-parameter mutation tool with an output schema and informative annotations, the description is nearly complete. It explains the draft/published distinction, the effect on existing runs, and where to find schema reference. It doesn't discuss failure modes or idempotency semantics, but given the rich schema and annotation hints, the description is sufficient for an agent to use the tool correctly.

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 100%, and each parameter (id, name, config, environment, workspaceId) has a clear description. The tool description adds no new parameter-level value beyond what the schema already states, such as 'replaces the whole DRAFT config' and the env/workspace grant requirements. Therefore the baseline score of 3 for fully covered schemas is appropriate.

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 description identifies a specific action (update), a precise resource (an extractor's mutable draft/extract group), and the scope of what can be changed (rename and/or replace draft config). It also explicitly distinguishes the draft from published versions, which prevents confusion with publish_extractor_version or get_extractor.

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 clearly implies this tool is for editing the mutable draft only, and notes that published versions are immutable and unaffected — a useful when-not-to-use boundary. It also advises calling get_documentation before hand-editing the schema, giving practical workflow guidance. It doesn't name alternative siblings explicitly (e.g., create_extractor), but the draft-vs-published contrast is strong enough for most routing decisions.

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