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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the description only needs to add context — which it does substantially: property order is preserved verbatim and drives editor field order, versions are immutable, an x-tessryx-ui hint is required for media/entity-reference/cron/color fields, and publish controls which version is live. These are non-obvious behavioral consequences an agent could not infer from 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?

The key scoping distinction is front-loaded in the first sentence, and every sentence carries information. It is dense — the x-tessryx-ui sentence is a parenthetical detour — but nothing is padding, and the closing exclusion is well placed.

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 annotations, a full schema description, and an output schema, the description covers the mutation's semantics, ordering side effect, highlighting prerequisite, and publish behavior. It omits what happens on invalid json_schema or a nonexistent schema_id, which is the main remaining gap for a write operation.

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 100%, so baseline is 3; the description adds real meaning on top — that publish=true is the one-step create-then-publish path and determines which version is live, and why property order in json_schema matters. It stops short of describing failure or validation behavior for a malformed json_schema.

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 ('add a new version to an EXISTING schema') and immediately scopes it to existing schemas by schema_id. It explicitly names the sibling it is not ('For a brand-new schema, use create_schema'), so an agent can distinguish it from create_schema and publish_schema without opening a 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?

Gives explicit when-to-use (evolve an existing schema), when-not (brand-new schema → create_schema), and names the alternative for publishing (publish_schema, or publish=true inline). It also routes to get_guide("schemas") for the x-tessryx-ui requirement, which is a concrete prerequisite condition.

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