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

Annotations only declare the safety profile (readOnly=false, destructive=false); the description adds real behavioral context beyond them: media and existing schedule are preserved, channel-specific tailored copy is untouched, the revision runs the voice engine server-side, and replaced words are recoverable from version history in DemandBird. That last point is the key reversibility disclosure for a mutation tool.

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?

Purpose and the anti-pattern warning are front-loaded, then preservation guarantees, then recoverability. Each sentence carries distinct information — no restatement of the title or the schema.

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 non-destructive mutation with no output schema, the description covers what an agent must know: which post is affected, what is preserved, what is recoverable, and which sibling not to use. There is no material gap that would cause a misinvocation.

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 description coverage is 100%, so the schema already documents id, feedback, platform, and draft_anyway thoroughly. The description adds only indirect semantic context (the revision touches the shared draft, not per-channel tailored copy), which helps interpret the platform parameter but is not stated as parameter guidance. Baseline 3 applies.

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 ('Apply the user's feedback to an EXISTING draft') and pins the outcome ('save the revision onto the SAME post'). It explicitly distinguishes itself from the nearest sibling, draft_post, so an agent can route correctly without inspecting schemas.

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 both sides of the routing decision: use this 'every time the user reacts to a draft you already produced', with concrete trigger phrases, and 'Do NOT call draft_post again to act on feedback', including the consequence of getting it wrong (a second draft plus an orphaned first draft with its images). Nothing is left to inference.

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