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

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing. It doesn't say whether generation is asynchronous (implied by the existence of get_research_status), whether an existing report is replaced or appended when 'extending', whether it consumes credits, or what triggers its failure mode.

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 with zero filler. It is efficient, though the efficiency comes at the cost of under-specification rather than by compressing real information.

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?

A five-parameter mutation-style job starter with no annotations, no output schema, and 20% schema coverage demands far more than one sentence. Nothing about async behavior, return value, side effects, or the four undocumented parameters is covered.

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 only 20%: notification_message is documented, but publisher_pid, report_only, included_sections, and require_product_name_in_queries are bare. The description adds no meaning for any of them — notably it doesn't explain what 'report_only' toggles or what sections may be requested, so an agent must guess at four of five parameters.

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 pair and resource: "Start or extend research for a project." An agent knows this creates or continues a research job on a project, but the description never contrasts with siblings like get_research_status or list_research_reports, so the agent must infer that those are read-only counterparts.

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?

"Start or extend" hints at when the tool applies but gives no explicit conditions, no prerequisites, and no named alternatives. Nothing tells the agent when to call this versus polling get_research_status or reading list_research_reports, nor when not to call it (e.g., research already complete).

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