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

With no annotations provided, the description carries the full burden, and it delivers: it flags 'WRITE' and 'SYNCHRONOUS' behavior, warns about the 30-60s runtime and 90s loopback timeout, explains the underlying thread call to AppsFlyer, and states the 31-day API cap. This is exemplary disclosure beyond what a schema could convey.

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 dense but every sentence earns its place, moving from the most critical behavioral warning first, then required params, then caveats, then an example. The block-structured formatting and sparing use of emphasis make the key constraints scannable. No filler.

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?

Despite high complexity and no annotations/output schema, the description covers purpose, mutation behavior, timing, timeout, API limits, parameter semantics, an anti-pattern, and a complete invocation example. An agent has everything needed to decide correctly and construct valid arguments. Missing return-format details are minor for selection and invocation.

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%, so the description must supply parameter meaning, and it does thoroughly: connection_id is specified as UUID, date_from/date_to are pinned to YYYY-MM-DD, the 'NOT start_date / end_date' naming is explicitly forbidden, and selected_source_refs is explained as a per-fetch override. The included JSON example solidifies the expected shape.

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 opens with a specific verb-resource pair — 'Fetch and persist cohort rows for one app under one MMP connection' — which clearly delimits the tool's scope and distinguishes it from generic fetch or config tools. It also labels itself a 'Mirror of Meta MCP mmp_fetch_cohorts,' reinforcing its exact identity among the mmp_* siblings.

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 provides clear context and constraints: use only as an explicit read refresh, never as an onboarding side effect, and only for date ranges ≤ 31 days. It does not explicitly name alternative tools or when to prefer them (e.g., mmp_refresh_connection or mmp_save_cohort_config), so it falls just short of full routing guidance.

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