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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description's addition of 'Execution: synchronous' and 'Task support: forbidden' provides some extra behavioral context not in the structured annotations. However, the description focuses more on how to present results than on operational behavior like error handling or auth requirements.

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 five sentences, but most are dedicated to output formatting and behavioral rules (e.g., 'Never display raw JSON,' 'Prefer concise, human language') that belong in a system prompt rather than a tool description. The first sentence is a tautology, and the structure buries any useful operational detail under generic agent instructions.

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?

Given the tool has 11 parameters and no parameter descriptions, the description fails to explain what an 'advertiser' is or how the various IDs (seatId, flightId, campaignId, etc.) relate. The output schema exists, which covers return shape, but the description's vague 'internal application state' does not compensate for the lack of parameter semantics or usage context.

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 0%, and the description does not explain any of the 11 parameters. It never mentions advertiserId, seatId, or other fields, leaving the agent to guess that advertiserId is the primary identifier. The description adds no semantic value for choosing or filling parameters.

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 'get advertiser,' which is essentially the tool's name and title, providing no elaboration on what exactly is retrieved or returned. It does not distinguish this tool from siblings like get_campaign or get_asset, and the rest of the text is about response presentation, not purpose.

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 guidance on when to use this tool versus alternatives like list_advertisers or update_advertiser. The instruction 'Use assistantSummary first' refers to response composition, not tool selection, and the 'suggest the next best LeanrIQ action' is generic advice that doesn't clarify the tool's intended use case.

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