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

Goes well past the annotations (readOnly, non-destructive, closed-world) by disclosing exactly what the exported artifact contains and, more importantly, what is redacted: no post id, profile id, or account details, and WhatsApp button links become a {link} placeholder. It also flags the sharp edge that non-button links and typed numbers are NOT blanked, telling the agent to check before sharing — genuinely actionable behavior an agent could not infer from structured fields.

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 purpose in sentence one, then layered with redaction rules and prerequisites in a logical order. Slightly padded — the message/trigger/keyword inventory and the 'only button links are blanked' restatement overlap — but nearly every sentence carries decision-relevant information.

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?

With no output schema, the description does the work of describing the return artifact (a file with trigger, keyword, message) and its redaction semantics, plus prerequisites and the draft limitation. The one gap is the delivery mechanism — it says 'Download' but never clarifies whether the caller receives a URL, a file reference, or raw content, which matters for a tool with no output 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?

Schema coverage is 100% for the single automation_id parameter, so the schema already carries the meaning. The description adds only an indirect constraint — the id must refer to a non-draft auto reply — without saying anything about id format or where to source it. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Download one Instagram auto reply as a shareable template') and implicitly scopes it against the import/create-from-template siblings by framing the output as something 'whoever imports it' consumes. An agent can distinguish this from sprkly_import_automation_template or sprkly_list_automation_templates 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?

Gives concrete preconditions and exclusions: the auto reply must not be a draft ('nothing published to export') and a connected Instagram account is required. It does not explicitly name the companion tool for importing or point at sprkly_list_automations as the way to obtain an automation_id, so routing is implied rather than spelled out.

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