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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description goes beyond this by defining the semantic domain (ads vs. marketplaces, no order sync), explaining the meaning of versionType ('primary' vs. 'secondary'), and disclosing that project_id is optional only under a specific condition (single-project customer vs. project_id_required). These are behavioral details the annotations do not convey, making the description genuinely informative.

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 longer than typical but every sentence carries essential information: the what, the domain disambiguation, the return structure, field semantics, and usage callout. It is well-structured: the primary purpose is front-loaded, followed by clarifying context, then parameter guidance. It is not padded with fluff, though it could potentially shorten the return-structure details since there is no output schema and they are necessary for the agent to understand the result.

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?

For a read-only getter, this description is unusually complete. It includes the full return payload shape with nested definitions, clarifies how to interpret versionType, states the exact ordering of use relative to list_ad_channels and create_ad, and covers the project_id edge case. No output schema is provided, so the description must carry the return contract — and it does. An agent has everything needed to invoke this tool 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?

With schema coverage at 50%, only channel_code has a schema description, and it is minimal. The description compensates fully: it explains channel_code's provenance ('from list_ad_channels'), describes project_id's optionality and the exact condition for when it is required, and maps both to their roles in selecting a definitionCode. This adds meaning beyond the schema's bare type constraints.

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–resource pair ('Get one ad channel's detail') and immediately narrows scope to 'integration TYPES it supports and each type's capabilities.' It explicitly differentiates ad channels from marketplaces ('Ads are ads-based channels... not marketplaces') and names the sibling tools it is not (list_ad_channels, create_ad). This leaves no ambiguity about what the tool does and how it differs from get_marketplace_channel.

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 when-to-use guidance: 'Call this before create_ad to choose the right definitionCode for the channel.' It also specifies where input comes from ('channel_code is the channelCode from list_ad_channels') and when the optional project_id is needed (project_id_required otherwise — then call list_projects and pass its project_id). This is direct operational guidance that an agent can act on without inference.

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