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

No annotations are provided, so the description carries the full burden. It does add one genuinely useful fact — that research starts in the background — but says nothing about that job being asynchronous, how to poll it, what happens on failure, whether creation is idempotent, or what permissions are required.

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?

One front-loaded sentence with no filler, which is structurally good. But the brevity here is under-specification rather than economy — the single sentence is the entire description for a 10-parameter, side-effecting 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?

For a complex creation tool with 10 params, no annotations, no output schema, and a background job, one sentence is nowhere near sufficient. Missing: parameter meanings, whether research is opt-in, return value (project ID?), and how it relates to get_project_initialization_status.

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?

Ten parameters with only 10% schema description coverage, and the description explains none of them. Cryptic names like promo, days_back, min_query, max_query, report_only and export_pdf are given no meaning anywhere, so an agent must guess at their semantics and types of values expected.

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?

A specific verb+resource ("Create a project") plus the non-obvious side effect of launching background audience research. It never distinguishes itself from siblings like generate_research or list_projects, so an agent can't tell from text alone whether create_project also does the research those tools appear to cover.

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?

There is no when-to-use guidance, no prerequisites, and no named alternatives. With siblings such as generate_research, get_research_status and get_project_initialization_status present, the agent is left to infer the ordering and whether the background research is optional or duplicated elsewhere.

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