Reply to and hide a comment

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

Goes well beyond the annotations: it discloses ordering semantics (reply first, so a failed reply hides nothing), the already-hidden case, the preview/plan_id divergence rule, non-idempotency ('never retry blindly'), reversibility of both steps, and required token scopes plus MODERATE task. The annotation idempotentHint=false is reinforced and explained rather than merely echoed.

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?

Front-loaded with the core action and an example, then constraints in roughly priority order. Dense with semicolon-chained clauses, but nearly every clause carries a distinct operational fact, so little is wasted.

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 two-step mutation with no output schema and a nested attachment object, the description covers the preview requirement, per-step outcome reporting, failure fallback, and auth needs — everything an agent needs to invoke it safely.

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 the baseline is 3; the description adds real workflow meaning on top by tying `apply` and `plan_id` to the mandatory preview step and warning that a comment changed between preview and apply makes the plan diverge. It does not re-describe message/attachment/comment_id, which the schema handles.

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 compound action — public reply under a comment, then hide that comment — and names the exact outcome ('We have sent you a DM' under spam/abuse). It is clearly distinguishable from siblings facebook_reply_to_comment and facebook_hide_comment because it explicitly describes the combined step.

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?

Gives the when (spam or abuse triage), the when-not/escape hatch ('if the hide fails, finish with facebook_hide_comment'), and the prerequisite flow (preview first, then apply with plan_id). Alternatives and conditions are explicit rather than inferred.

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