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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds valuable beyond-annotation details: execution is synchronous, task support is forbidden, the returned JSON is internal orchestration state, and missing scope results in INVALID_INPUT rather than an empty result. These clarify expected behavior and failure modes. 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 overly long and front-loaded with a tautological opening. Much of the content is generic response-handling instructions (never display raw JSON, use assistantSummary first) that apply to many tools, not specific to get_asset. While the scoping details are well-structured, the response-formatting boilerplate could be omitted for conciseness. Two or three sentences could convey the essential behavioral guidance.

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's complexity (11 parameters, numerous sibling get_* tools), the description is incomplete. It doesn't differentiate this tool from get_creative or get_advertiser, doesn't explain the remaining parameters, and creates ambiguity by mentioning 'listing assets' without specifying the tool for that action. The output schema exists, so return values aren't a gap, but the parameter semantics and tool-selection context are insufficient.

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%, so the description must compensate. It explains the roles of assetId, advertiserId, and creativeId (as scopes), but entirely ignores the other 8 parameters (seatId, flightId, campaignId, etc.). These parameters may be filter or context fields, but their meaning and usage are never addressed. The description only partially clarifies the most critical parameters, leaving a significant semantic gap.

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 the tautological phrase 'get asset' and only indirectly states its purpose via 'when retrieving one asset.' It implies retrieval of an asset's internal state but doesn't clearly define what an 'asset' is or how it differs from sibling tools like get_creative or get_advertiser. The scoping requirement (advertiserId/creativeId) hints at a specific resource type but lacks explicit differentiation.

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?

Provides usage context for scoping: 'pass one of those scopes together with assetId when retrieving one asset' and warns about INVALID_INPUT. However, there is no explicit guidance on when to use this tool versus alternatives like list_assets or get_creative. The instruction to 'Use assistantSummary first' is about response formatting, not tool selection. The guidance is implied rather than explicitly contrasted with sibling tools.

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