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

The annotations already declare destructiveHint=true and idempotentHint=true, and the description goes beyond them with genuinely new behavioral facts: reactions are visible to the counterparty, are approval-exempt but still rate-limited and logged, and one-per-message with replacement semantics. The replacement rule is the critical detail an agent could not infer from annotations and is exactly what prevents an accidental overwrite.

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, front-loaded with the action verb and followed by the constraints that matter most. The parenthetical on approval-exempt/authorized/rate-limited/logged is slightly dense and tangential, but no sentence is pure filler.

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 destructive, idempotent, open-world mutation with an output schema already documenting returns, the description supplies the replacement rule, visibility, and operational guarantees an agent needs. What is missing is permission/authorization specifics and the emoji-required-for-set rule, which remains entirely on the schema.

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?

With only 33% schema description coverage, the description must compensate, and it partially does: 'set or remove' maps onto the action enum and its replacement behavior. But it never explains the action-conditional requirement for emoji (the schema covers only that one field), nor the numeric message_id constraint, leaving real semantic gaps.

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?

The first sentence gives a precise verb pair plus resource and scope: 'Set or remove this account's emoji reaction on a message.' That is unambiguous about what is mutated and whose reaction it is. It stops short of naming the adjacent operations it could be confused with (manage_pin, manage_star, update_labels), so it lands at 4 rather than 5.

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?

The set/remove dichotomy plus the note that a new emoji replaces the old one implicitly tells an agent what each invocation is for. However, there is no explicit when-to-use guidance, no exclusions, and no routing to sibling tools such as manage_star or manage_pin, which are the most plausible confusions for an agent scanning this toolset.

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