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

Goes well beyond destructiveHint by disclosing the acting identity ('as the connecting person when the workspace has user-token reactions:write, otherwise as the app') and the idempotency behavior (removing an absent reaction succeeds). Both are behavioral facts an agent cannot derive from the annotation, making this genuinely additive.

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 the sibling it inverts, then layers identity and idempotency details in a single dense paragraph. The trailing channel sentence largely duplicates the schema's channel description, a small redundancy that keeps it from a 5.

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 4-parameter mutation with no output schema and full schema coverage, the description supplies everything else an agent needs: identity/auth rules, idempotency, and sibling relationship. Nothing material is missing.

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 every parameter is already documented in the schema, including the composite 'channel:ts' acceptance the description repeats. The description's channel note adds no syntax or meaning beyond the schema, so the 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+resource ('Remove an emoji reaction from a Slack message') and explicitly frames itself as 'the reverse of add_reaction', mapping it to the sibling it inverts. An agent can distinguish it from add_reaction and get_reactions without opening any schema.

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?

Maps the tool against add_reaction explicitly and implies read/query alternatives, and gives a clear context cue (already-removed reactions are a no-op). It stops short of an explicit 'use X instead when Y' routing rule for the other reaction tools, but the usage context is unambiguous.

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