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

Annotations already carry the safety profile (destructiveHint=true, readOnlyHint=false, idempotentHint=true), and the description adds genuinely new context: replacing the whole draft config destroys prior draft state, published versions and runs pinned to them keep working, and agents should follow llmContext guidance in results. No contradiction with annotations — destructiveHint=true aligns with the whole-config replacement warning.

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?

Three sentences with the core purpose front-loaded and no filler. The get_documentation pointer and llmContext note each earn their place as behavioral guidance, though the parenthetical with the full URL makes the middle sentence slightly dense.

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 the output schema, annotations, and 100% schema coverage, the description only needs to convey lifecycle behavior — and it does: draft mutability, published immutability, and pinned-run stability are all covered. Complete enough for an agent to invoke correctly, with minor room for explicit sibling routing to publish_splitter_version.

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%, so name, config, id, workspaceId, and environment are fully documented in the schema itself. The description adds only the framing that rename and config replacement are independent optional operations ('and/or'), a marginal increment over the schema's own config description. Baseline 3 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?

States a specific verb and resource — 'update a splitter's mutable draft (split group)' — and enumerates concrete actions: 'rename it and/or replace the draft config.' The explicit draft-vs-published contrast distinguishes it from create_splitter, publish_splitter_version, and get_splitter without needing to name them. Scope is unambiguous.

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?

Frames when the tool applies (drafts, not published versions) and warns that published versions are immutable and unaffected, telling the agent this is not the tool for altering released configs. It also routes config hand-editing to get_documentation with a direct URL. It stops short of explicitly naming sibling alternatives such as publish_splitter_version for the publishing step.

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