edit_draft

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false). The description adds genuinely valuable non-obvious behavior beyond that: source always remains unchanged, gaps are preserved, no implicit ripple editing, and each operation's exact shape. This is exactly the kind of behavioral color the annotation layer cannot provide.

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 compact — a single purpose sentence plus a dense operation list that earns its place. The operation examples are front-loaded and each token adds information. It is somewhat dense in the middle but appropriately so for a tool with a five-parameter schema and zero param help.

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 tool with no output schema, 5 params, and a mutation-like behavior, the description covers the operation model thoroughly but omits the semantics of dry_run and include_plan — both of which shape what the tool returns. Without an output schema to fill the gap, an agent cannot predict the call's result shape or how the dry-run/plan modes behave.

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 0%, so the description carries the full burden, and it does compensate for the hardest parameter by documenting the operations array in detail (a field that is otherwise an untyped 'additionalProperties: true' bag). However, it leaves dry_run (which defaults to true — a surprising default), include_plan, name, and new_name unexplained beyond what their names imply, leaving meaningful gaps.

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 opens with a specific verb+resource phrase — 'Create a new revision of an MCP-managed project; source always remains unchanged' — which clearly defines the action and distinguishes it from an in-place edit. The operation catalog (append/remove/update/split) and the explicit 'gaps are preserved / no implicit ripple editing' statements further differentiate it from siblings like ripple_delete and batch_edit.

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 gives strong operational context: how to express edits (ops list), the fact that trimming/moving goes through update, and a pointer to read_managed_project for obtaining IDs. However, it never explicitly names alternatives or states when not to use this tool; the 'no implicit ripple editing' exclusion only implies that a sibling handles ripple deletion.

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