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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the description doesn't need to restate safety. It still adds real behavior: partial-edit semantics, the two-phase confirm/edit_token approval flow with the same patch, and the refusal of voice_map in favor of set_workflow_voice. It never characterizes what removal actually destroys or that all operations are atomic — that detail lives only in the schema.

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?

Front-loads the core idea and the sibling disambiguation in two short paragraphs. 'Everything the operations skip is kept' slightly duplicates the schema's 'Anything they do not name is kept', and the trailing 'Voices: set_workflow_voice' fragment is terse but earns its place as a redirect.

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?

With a rich schema, full annotation coverage and an output schema, the description covers the remaining model-facing decisions: patch vs full update, the confirm/token handshake, and the voice exclusion. Only operational limits (max operations, ordering, all-or-nothing application) are left to the schema, which is acceptable given its depth.

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 confirm, edit_token, workflow_id and patch are all documented in-schema; the description only reinforces patch semantics and the token round-trip. It adds no syntax or constraint detail (e.g. the 200-operation cap) beyond what the schema already says, so baseline 3 is right.

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 ('Change part of a saved workflow') plus the defining property of a patch — untouched state is preserved. It names the sibling it replaces (update_workflow) so the agent can separate the two without opening either 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?

Explicitly routes ordinary edits (threshold, config key, node add/remove, connection redraw) here rather than to update_workflow, and gives concrete example edits. It also states the required call sequence (unconfirmed call for an edit_token, then repeat with confirm=true) and where voice changes belong instead.

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