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

Annotations already declare non-destructive, idempotent, non-read-only behavior, so the bar is lower; the description still adds real value by stating that only the draft is mutated and published content is never touched. It omits permission/auth requirements and whether omitted fields are left untouched.

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-loaded with the one-line purpose, then the payload routing rule and the override key list. The long parenthetical is dense but earns its space because the schema's own `overrides` description is circular ("keyed as described above"), so the description has to carry that enumeration.

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 9-param nested-object mutation with an output schema and full annotations, this covers the decisive choices (which payload path, draft-only scope, what fields are editable). The remaining gap is replacement semantics — whether passing `spec` overwrites the whole definition — and the access_level/group_ids pairing.

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?

At 56% schema coverage with 9 params and nested objects, the description compensates: it disambiguates `spec` vs `overrides`, spells out the override key space (entry.card, steps by id, output.extra_guidance, settings.expire_after_minutes) that the schema only gestures at, and maps `enabled` to the switch plus `access`. It does not connect `access_level: groups` to `group_ids`, and `group_ids` itself is never explained.

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?

"Update a Zuno flow's draft" gives a specific verb and resource with explicit scope, and "Never changes what is published" cleanly separates it from publish_flow and unpublish_flow. An agent can distinguish it from create_flow, get_flow and validate_flow without opening any 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?

It states the routing rule between the two mutually exclusive payload paths: pass `spec` for a custom or template-copy flow, `overrides` for a nunify flow. It does not name the alternative tools (validate_flow, publish_flow) or explicitly say when not to use this, but the draft-only scope implies where the boundary lies.

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