Read comments on a Meta post

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

Adds crucial non-obvious behavior: replies are nested and not returned by the post, requiring a recursive call with the comment id. Also discloses that each row shows reply counts, which informs the agent about output structure. Annotations already cover readOnly/non-destructive, so description enriches with reply semantics.

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 sentences with no fluff. The reply explanation is dense but necessary. Front-loads purpose and use case, then addresses the complexity. Well-structured for an agent to scan.

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?

Covers the key pitfalls (reply nesting, pagination caveat via schema) and provides actionable guidance. Does not enumerate all output fields, but without an output schema, the description still gives sufficient context for a read operation. Slightly incomplete on pagination behavior, but schema compensates.

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?

While schema covers 100% of parameters, the description adds meaning beyond schema: explains that postId can be a comment id to retrieve replies, and clarifies the purpose of count/cursor in context. This is valuable semantic addition beyond the basic schema text.

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 clear verb-resource pair: 'Read the comments under a Facebook Page post or Instagram media object'. Distinguishes itself from sibling write/moderate tools by positioning as the read step. The mention of 'customer questions, objections and exact language' adds useful context.

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?

Explicitly says it's 'the first step before replying or moderating', giving clear when-to-use context. Provides detailed instruction for fetching replies by setting postId to a comment id, which is essentially an alternative usage path. Doesn't explicitly list exclusion criteria (e.g., use list_meta_posts for posts), but the distinction is implicit.

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