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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the description's added value is in specifics: it states that existing campaigns and saved sequences are untouched, and it explains the retry contract (same key plus same input returns the first result rather than repeating). It does not describe the response body or any permission requirements, keeping it below a 5.

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 short sentences, front-loaded with the core action, then scope, then retry semantics. The idempotency sentence partly restates idempotentHint=true, but it adds the concrete "returns the first result" behavior, so it earns its place.

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, idempotent create with no output schema, the description covers side effects and retries adequately, but the nested body remains the largest unknown: an agent cannot tell from the description how `sequence`, `source_template_id`, and the campaign revision/strategy ids relate, nor what the call returns (e.g., the new template id).

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%: idempotencyKey is documented in the schema, but the nested body object has five properties (name, sequence, description, source_template_id, campaign_strategy_id, campaign_messaging_revision_id) with no descriptions, and `sequence` is an untyped free-form field. The description mentions idempotency reuse (already in the schema) and hints at copying from a campaign, but never explains what `sequence` should contain or how source_template_id differs from campaign_strategy_id, so it does not compensate for the coverage gap.

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 ("saves a new reusable message sequence") and clarifies the typical input source ("for example from a campaign's sequence"). It distinguishes creation from get/list/archive siblings by implication, but never explicitly addresses duplicateSequenceTemplate, which also produces a new saved sequence, so the boundary is not fully clean.

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 phrase "for example from a campaign's sequence" gives an implied usage context: snapshotting an existing campaign sequence into a reusable template. There is no explicit when-not guidance and no named alternative for the common confusion with duplicateSequenceTemplate or createCampaign, leaving selection partly to inference.

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