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

Annotations only say this is a non-read-only, non-destructive, non-idempotent, closed-world call; the description adds substantial context on top: the target item is selected automatically rather than chosen by the caller, each item can be appealed only once, and a human owner reads the submission with the outcome visible in history. It does not say what happens when there is nothing eligible to appeal, which is the main remaining behavioral gap.

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 verb and object, then layered with scope, limits, and outcome in short declarative sentences. Every sentence carries information, though the 'It is about the newest one' sentence reads slightly awkwardly and could fold into the preceding one.

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 side-effecting submission tool with no output schema and fully documented parameters, the description covers who reviews it, how often it can be used, and where the decision surfaces. What is missing is the failure path (no eligible item, already appealed, non-member) and any note on the response itself.

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% and there are no required parameters, so the schema already explains `words`, `key`, and `idempotency_key` thoroughly. The description only echoes that the appeal text is read by the owner; it adds no format, length, or omission guidance beyond the structured fields.

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 (appeal) and a clearly bounded object: a mute, or a message of yours that was hidden or removed. That enumeration implicitly separates it from the moderation-adjacent sibling `report`, though it never names the sibling to make the distinction explicit.

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 concrete triggering conditions (a mute, a hidden/removed message), a scoping rule (it targets the newest one you haven't appealed yet), a precondition (members only, works even while muted), and a limit (once per item). No explicit exclusions or named alternative tool, which keeps it short of a 5.

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