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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive write, so the safety profile is covered. The description adds real value with the optimistic-concurrency contract for `base_version` (guarding against clobbering a newer version) and the statement that type is preserved. However, it mentions `app_url` in the result despite an output schema existing, which is redundant, and says nothing about permission requirements, what happens to prior media, or whether versions are retained.

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?

Four short clauses, front-loaded with the core effect, and no filler. The parenthetical about artifact_feedback is slightly tangled and the semicolon-plus-parenthetical structure reads awkwardly, but every clause carries information.

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 an 11-parameter mutation tool, the description covers the two things an agent is most likely to get wrong: which input combination to supply and how to avoid stale-base overwrites. Completeness is limited by its decision to outsource input-kind semantics to create_artifact without restating them, and by silence on change_note and on what happens to existing media/content that isn't re-supplied.

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 64%, so about a third of the 11 parameters rely on the description. It explains `base_version`'s conflict-avoidance purpose and the 'content alone' shortcut, plus that `type` is carried over rather than changed. It does not help the agent choose among `html`, `markdown`, `body_md`, `media_ids`, and `upload_id`, deferring entirely to create_artifact, and it never mentions `change_note`.

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 identifies the operation as producing a new version of an existing artifact and notes that type is preserved, which lets an agent separate it from create_artifact (new artifact) and artifact_feedback (feedback on agent work). The opening is a noun phrase rather than a verb ('A new version of an artifact...'), so the action is inferred rather than stated outright, but the resource and effect are unambiguous.

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 gives one explicit routing rule: agents' work is revised through artifact_feedback rather than this tool, which is a genuine when-not statement naming an alternative. It also clarifies that all input kinds from create_artifact are accepted, or `content` alone. It stops short of saying 'use this only when the artifact already exists and you want to modify it', leaving the create-vs-revise boundary to be inferred.

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