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

The description adds real behavioral context (synchronous execution, forbidden task support, mutation modes, completed_items_not_rolled_back partial-failure policy, deterministic idempotency-key derivation, per-call seat requirement). But it labels the tool read-only while annotations declare readOnlyHint=false and it elsewhere discusses mutations and seat rules for writes — a direct conflict that will confuse an agent about whether this call mutates state.

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 purpose is front-loaded and the operational notes are ordered sensibly, but the opening sentence is duplicated from the title with a double period, and a large block of generic orchestration advice (assistantSummary, never display raw JSON) is boilerplate that does not earn its space for this specific tool.

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?

An output schema exists, so return values need not be described. However, for a 16-parameter tool with deeply nested identity/context objects at 0% schema coverage, the description supplies almost no parameter-level or structural guidance, leaving an agent unable to construct a correct call from the definition alone.

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% across 16 top-level parameters, including large nested objects (advertiserContext, marketContext), so the description carries the full burden. It explains only the seat-scoping rule for seatId/seatName and references idempotencyKey (which is not even in the schema); the remaining parameters and nested fields are left entirely undocumented.

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 gives a specific verb and resource ("Build a versioned advertiser research graph from configured identity and approved context") and identifies itself as a deprecated alias for build_world_research_profile, which is useful differentiation. However, it lazily repeats the title verbatim with a double period, and the simultaneous "Classification: read-only" and "Mutation modes: validate_only, preview_only, execute" framing muddles what the tool actually is.

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?

Labeling itself a deprecated alias implies the canonical build_world_research_profile should be preferred, which is a usable routing signal. But it never states the condition for choosing this alias over the canonical tool, nor any prerequisites beyond the generic seat sentence, so the when-to-use guidance is only implied.

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