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

Annotations mark this non-read-only and open-world, but the description supplies the behavioral detail they cannot: it is always a draft, nothing goes live even on a publishing connection, repeats update the same CMS document, refusals carry reasons, and the slug-collision error enumerates CMS ids, titles, draft states and owning posts. useCmsPageId replaces another page's content, which is worth knowing given destructiveHint=false, though the replacement stays scoped to a draft and does not rise to a contradiction.

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?

Three dense paragraphs with the core action front-loaded in the first sentence and 'Related:' cross-references last. It is longer than most definitions, but nearly every clause carries distinct operational information (state guards, idempotent-update behavior, conflict routing, slug collision payload).

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?

An output schema exists, so return values need no explanation, and the description covers the remaining agent-relevant surface: entry conditions, refusal taxonomy, recovery paths, and cross-references to get_post, save_post, approve_posts and resolve_cms_conflict. Nothing needed to invoke it correctly is missing.

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 both parameters are already documented and the baseline is 3. The description goes further by explaining how useCmsPageId is actually obtained (the ids a refusal lists as acceptable), its side effect of replacing the target page's content, and that the page then becomes this post's page permanently.

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 with scope: saves an unapproved post (draft, changes requested, in review) to its website CMS as a draft for on-site review. It is immediately separable from siblings like approve_posts, save_post and resolve_cms_conflict, and it explicitly notes what it does NOT do ('Does not approve or change the post's status').

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?

Explicit preconditions (post must be in draft/changes-requested/in-review), explicit refusal conditions (approved, scheduled or published post; channel with no CMS mapping; collection without drafts), and explicit alternatives for each refusal case (save_post to change the slug, useCmsPageId to target an existing page, resolve_cms_conflict for overwrite/keep).

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