mutate

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 does disclose one genuinely useful behavior beyond the schema: passing a UUID idempotencyKey makes retries safe because a replay returns the original result instead of double-creating. However, for a delete-capable mutation tool it says nothing about permission requirements, reversibility of deletes, or batch atomicity.

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 dense sentences that are front-loaded with the core purpose before drilling into action values, payload shape, and idempotency. The eight-value action enumeration is long but earns its place since the schema omits the enum.

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 4-parameter, nested-object mutation tool with no annotations and no output schema, the description covers action semantics, payload shape, and idempotency, but leaves projectId undefined, gives no sense of what a successful response contains, and omits permission and reversibility context that an agent needs before issuing deletes.

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 coverage is only 25% and the schema types 'action' as a bare string with no enum, so the description's enumeration of the eight legal action values is essential compensation. It also clarifies that payload carries the remainder of the mutate body with concrete shapes (node | nodeId+data | mutations | iteration) and that idempotencyKey is a UUID. projectId is left unexplained, keeping it from a 5.

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 gives a concrete verb+resource: create/update/delete plan nodes and phases, and enumerates the eight supported action values, which is far more specific than the bare name 'mutate'. It does not explicitly distinguish itself from read-side siblings like list_nodes or get_tree, so it stops short of a 5.

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 action list implies the usage modes (add/update/delete/batch/iterations/classify) and the idempotency hint implies retry scenarios, but there is no explicit when-to-use versus alternatives, no exclusions, and no prerequisite guidance (e.g., which sibling to call to obtain nodeId before mutating).

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