zuckerbot_get_creative_attributes

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

Even with no annotations provided, this description carries the full behavioral load: it discloses the read-only nature, confirms no extraction is triggered, confirms no spending occurs, and details included lifecycle fields such as tag_status, error_class, attempt metadata, and version/fingerprint information. That gives the agent an accurate mental model of what will happen.

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?

The description is packed with useful information but remains organized and front-loaded with the core 'read' action and resource. The three long sentences are dense, yet every clause adds context about shape, lifecycle, read-only behavior, or intended usage. It is borderline long but not bloated given the lack of an output schema.

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?

The description compensates for the missing output schema by enumerating the returned shape: 17 extracted attributes, lifecycle, versions, fingerprints, and objective family. It also provides the correct temporal context relative to sibling tools. The main gap is unspecified behavior for invalid or missing ad IDs, but all core retrieval aspects are covered.

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 each parameter already has a meaningful description. The natural-language description adds context such as the 'up to' limit and the canonical data shape, but it does not materially extend the schema's parameter-level explanations. A baseline of 2 is therefore appropriate: the schema handles the load.

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 description begins with a specific verb and resource: 'Read the stored creative attribute tags' in the 'canonical creative_attributes.v1 shape'. It clearly distinguishes this from sibling analysis tools by emphasizing that it only reads already-stored rows rather than running analysis or extraction.

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 description gives explicit sequencing: use after zuckerbot_audit_account reports creative analysis complete, or before zuckerbot_creative_analysis to inspect individual ads. It also signals the safety aspect, 'never triggers extraction and never spends anything,' which tells the agent when low-cost inspection is appropriate. It does not enumerate all exclusions, but the contextual guidance is strong.

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