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

Annotations already provide readOnlyHint=true and destructiveHint=false, and the description reinforces and extends this with 'Read-only, 0 credits' and 'Only ever reads a Page the brand has connected.' It also discloses important edge behaviors not in annotations: Instagram Stories are excluded, Facebook hides unpublished drafts unless requested, and the tool can surface postIds for later reads. This goes well beyond the structured data.

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 description packs a lot into a single paragraph and front-loads the core purpose and scope. The all-caps sentence and the historical aside about the only previous way to obtain a postId are slightly verbose, but each sentence contributes distinct value: scope, purpose, use cases, parameter quirks, constraints, and cost.

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 read-only tool with 6 optional parameters, no output schema, and multiple edge cases, this description is complete: it lists the returned fields, names the dependent tools, covers Stories exclusion, unpublished drafts, credit cost, and the account target behavior. An agent has enough to call it correctly and to explain its result to a user.

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?

The input schema already has 100% description coverage, so the baseline is 3. The description adds practical meaning beyond the schema: 'Pass target:'instagram' for the linked IG account' clarifies the enum option, and 'Facebook hides unpublished drafts unless you ask for them' explains the real-world effect of includeUnpublished. It doesn't add much for limit/cursor/pageId, but the schema handles those.

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 starts with a specific verb and resource: 'List the connected Facebook Page's or Instagram account's OWN existing posts' with an explicit field list (id, caption, permalink, publish date, format). It strongly differentiates from siblings by emphasizing 'OWN' posts and positioning itself as 'THE TOOL THAT GETS YOU THE postId every other Meta read needs' — an agent can immediately tell it apart from list_published_posts, post_performance, and backfill_posts.

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?

The description gives explicit use cases: 'Use it for "how did our last few posts do", to find a post the user describes loosely, or before backfill_posts.' It also names dependent tools (meta_post_insights, list_meta_comments, manage_meta_post) and the previous fallback (post_to_meta), which tells the agent exactly when this tool is the right route rather than a sibling.

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