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

Annotations already establish this as a read-only, idempotent, non-destructive, closed-world call, so the safety profile is covered. The description adds real behavioral value beyond that: completed research and pictures carry their result, and pictures expose per-component progress via items, which tells the agent what a terminal vs in-progress response looks like.

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?

A single front-loaded sentence covers purpose, scope, and return behavior with no filler. It is dense, and the trailing clause about pictures/items could be split for readability, but nothing is redundant.

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 polling tool with no output schema, the description conveys enough: which operation families are valid, that results appear when complete, and how paginated picture results are structured. The only gap is how an agent acquires the operation_id, a minor omission given the schema's required-field marker.

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 50%: cursor is fully documented in the schema, while operation_id has only format/pattern constraints and no description. The description references operation_id implicitly and clarifies that results may be paginated ('items', per-component progress), but does not define what an operation_id represents or where the agent gets one, so it only partially compensates.

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 (returns current state) and resource (operation), and enumerates the exact operation categories it covers: provisioning, campaign creation, launch, company research, and prospect picture. No sibling tool provides operation status, so an agent can route to it without ambiguity.

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 implies usage by naming the operation types it serves, which nudges the agent toward polling after create/launch/research calls. However, it never states when to call it versus alternatives, nor when/whether to poll repeatedly or how to obtain the operation_id in the first place.

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