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

With no annotations, the description carries the behavioral burden. It discloses that no standalone material tokens are returned, each material_reference belongs to the same result item, and no exact total is present – all non-obvious traits that prevent misuse. It is clearly a read operation and does not contradict anything. It could mention pagination limits or response structure, but the key behavioral warnings are present.

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 long but every sentence serves a purpose – the main purpose, then three clarifying notes and a pointer to an alternative. It is front-loaded with the core definition, and the notes are terse. It is not bloated, but a more compact phrasing might be possible without losing meaning.

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 complete schema coverage and no output schema, the description is nearly sufficient. It covers the purpose, fields returned, and critical usage constraints. The only omission is a description of the overall response structure (e.g., whether it is a flat list or nested), which might affect parsing, but it is not essential for calling the tool.

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 coverage is 100%, so the schema already explains each parameter. The description adds practical meaning by linking the pagination parameters to the note about not counting by paging, and the 'by delivery performance' phrase enriches the sort_by semantics. This is a small but real increment over the schema, so above the baseline 3.

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?

States a specific verb and resource: 'List a game advertiser's creatives by delivery performance', and enumerates the fields returned (material_reference, delivery dates, heat, reuse status, media). It explicitly differentiates from the sibling tool get_game_platform_stats by naming it for platform totals, so an agent can distinguish this from related list tools without opening schemas.

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 explicit when-not-to-use guidance: 'No exact match total is returned' and 'never count by repeatedly paging', and names the alternative for totals (get_game_platform_stats). This is concrete and actionable, leaving no ambiguity about when to use this tool versus a sibling.

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