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

Annotations already carry readOnlyHint/idempotentHint/openWorldHint=false, yet the description still adds real value: the returned state vocabulary, the meaning of waiting_on_you relative to the caller, the you_can permission flag, and the business rule that approval-gated brands only queue approved posts. It redundantly restates "Read-only" and says nothing about result volume or paging, keeping it below 5.

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?

Scope is front-loaded and every clause carries information (states, waiting_on_you, you_can, version_id, sibling routing, business rule). The telegraphic fragment style and long state enumeration make it dense, but there is little genuine waste.

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 no output schema, the description does the heavy lifting on return values (states, waiting_on_you, approver, note count, version_id, you_can) and covers the downstream actions. Gaps remain around pagination/result limits and the purpose of user_goal, and the state vocabulary overlaps confusingly with the filter enum.

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 75%, so the baseline is 3. The description mentions filtering by state and due but adds no enum semantics, and it actually lists states (scheduled, published) that are not in the state filter's enum (which offers draft), which could mislead an agent about valid filter values. The user_goal parameter goes unmentioned.

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 pins down both the resource (a brand's social posts in team review) and the exact payload shape: each post's state, waiting_on_you, approver/changes requester, open note count, and version_id. It also distinguishes itself from the action siblings (review_post, comment_on_post_review, send_post_for_client_review), so an agent knows this is the read/listing side of the review workflow.

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?

"Filter with state and due" plus explicit routing to review_post/comment_on_post_review/send_post_for_client_review tells the agent when to read versus when to act. The approval-requirement note adds useful context. It stops short of stating exclusions versus other listing tools (e.g. list_content_drafts, get_post_publish_status), so it's strong but not exhaustive.

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