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

Annotations declare readOnly=false, destructive=false, openWorld=true and non-idempotent, but say nothing about side-effect visibility. The description supplies exactly that missing context: sending is public and immediate, requires an explicit in-chat confirmation, and is length-constrained (1–1,000 chars, 150 for TikTok public replies). That is material behavioral disclosure beyond the structured fields.

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 tight sentences, front-loaded with the action taxonomy then the safety gate then the limits. Nothing is redundant, though the TikTok 150-character note is slightly compressed and could read as a general limit at first pass.

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 public, open-world mutation with no output schema, the description covers the essentials: what each action does, the confirmation requirement, and character limits. It stops short of describing batch behavior (max 50 decisions, partial failures) or the return value, but those are secondary for correct invocation.

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?

Top-level schema coverage is 0%: neither 'project' nor 'decisions' is documented in the schema. The description does explain the three action meanings and the text length bounds, which matches the nested schema descriptions, but it never mentions the 'project' parameter or clarifies where reply_id values come from.

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 ('applies the user's decisions on drafted replies') and enumerates the three concrete actions available: send as drafted, send with a new text, save without sending, skip. An agent can immediately tell this is the execution step for drafts, distinct from listing tools.

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 explicit per-action semantics plus a hard precondition: show the exact final text and act only on the user's explicit yes in this chat. It does not, however, route the agent relative to siblings like list_pending_replies (where reply_ids come from) or publish_video/approve_video, so the boundary between this and other approval tools is left implicit.

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