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

Annotations already flag destructiveHint=true, and the description earns its keep by explaining the mechanism of destruction: data is a full replacement, and dropping the flow_source_id of existing buttons or select menus deletes their flows. That is exactly the kind of consequence an annotation cannot convey. It does not discuss permissions, reversibility, or recovery after a bad write.

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?

Two dense sentences, front-loaded with the operation, followed by the replacement warning and the concrete pitfall. No restated name/title, no 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 6-parameter mutation tool with a nested free-form object, no output schema, and intermediate schema coverage, the description supplies the prerequisite read step and the highest-risk side effect. Minor gaps: whether omitted fields are left unchanged versus cleared, and what a version conflict returns (the latter is partly handled by the version parameter's schema text).

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 coverage is only 50%, and the description compensates by mapping 'name, description or content' to the name/description/data parameters and by adding a nested-object constraint on data ('keep the flow_source_id of existing buttons and select menus') that the schema leaves completely open. message_id and the partial-update semantics of optional fields remain unaddressed.

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 concrete verb and resource ('Changes the name, description or content of a message template') and enumerates the mutable fields, so the agent knows exactly what is modified. It is clearly distinct from create_message/get_message by implication, though it never names a sibling explicitly.

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?

Provides explicit workflow guidance: 'data replaces the whole message, so start from get_message.' That is a real when-to-use rule that routes the agent to a prerequisite tool. It lacks an explicit when-not-to-use clause (e.g. prefer create_message / edit_flow), so it stops 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.