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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds extra behavioral context: execution is synchronous, task support is forbidden, the JSON is internal application state, and there are explicit instructions on how to present results. This goes beyond the structured annotations and helps the agent handle the response appropriately. No contradiction with annotations.

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 relatively concise and front-loaded with the primary purpose. It uses structured labels (Classification, Execution, Task support) and gives clear response-handling rules. Minor issues include a typo ('reporting..') and a slight ramble into presentation style, but overall it is organized and not redundant.

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?

Despite having an output schema, the tool is complex (15 params, nested objects) and the description provides no information about what delivery data is returned, how media_buy_ids are used, or what filtering options exist. The description focuses on output formatting rather than tool function, leaving the agent underinformed about when and how to invoke it effectively.

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?

The schema has 15 parameters and 0% description coverage. The description provides no explanation of any parameter (e.g., media_buy_ids, start_date, end_date, filters). Since the schema alone is insufficient for an agent to know how to populate fields, the description's complete lack of parameter guidance is a major deficiency.

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 states the tool provides 'AdCP-standard media-buy delivery reporting,' which indicates a specific resource and action (reporting on media buy delivery). It is distinct from sibling getters like get_flight or get_campaign by focusing on media buy delivery. However, it does not specify what metrics or data are included, leaving some ambiguity.

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?

There is no explicit guidance on when to use this tool versus alternatives. It mentions the returned JSON is for 'LeanrIQ and ChatGPT orchestration' and gives response-formatting instructions, but these are not usage criteria. No exclusions or alternative tool references are provided, so the agent gets no clear decision support.

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