zuckerbot_capi_status

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

No annotations are provided, so the description carries full responsibility and handles it well. It warns that 'attributed' does not mean Meta-side event matching, explains attribution requires leads_retrieval permission and a bounded backlog resolution, and instructs agents to read attribution.basis and attribution.note before drawing conclusions. This is precisely the kind of behavioral nuance that structured metadata cannot convey.

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 two sentences with a clear front-load: what is returned, followed by an IMPORTANT caveat block. Every clause either introduces a needed metric or prevents a dangerous misinterpretation. The extra warning length is justified by the ambiguity of the 'attributed: 0' case.

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 itself names all metric categories present in the result: total events, events per type, match quality, identifier coverage, meta_events_received, and attribution counts. It also discloses the permission requirement and the heuristic nature of attribution. An agent given this description plus the optional parameter schema has enough context to call the tool and interpret its output correctly.

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% since selectable_details/uses. The input schema already states that business_id is an optional business ID override, and the description does not add further parameter-specific semantics such as default behavior, allowed values, or relationship to the current business. Baseline 3 is appropriate because the parameter meaning is already fully documented in the schema.

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 opens with a specific verb and resource: 'Get 7-day and 30-day CAPI delivery statistics for the business', then enumerates the exact metrics returned. The metric specificity distinguishes it from nearby CAPI siblings such as zuckerbot_get_capi_config, zuckerbot_capi_test, and zuckerbot_send_capi_event without needing to name them.

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 implies this is the tool for reading CAPI delivery statistics, but it does not explicitly state when to use this tool versus alternatives or when not to use it. The guidance it provides is about interpreting result fields (e.g., delivery health is meta_events_received, not attributed), rather than tool-selection context.

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