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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description adds substantial operational context the annotations don't carry: synchronous execution, 30-60s duration, 90s loopback timeout, and the AppsFlyer 31-day API cap. It does not reconcile the destructiveHint flag (what existing rows are overwritten), which is the one gap.

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?

Front-loaded purpose, then the WRITE/sync warning, then required params, date constraints, optional param, and a concrete example. Every line adds operational value and the sectioning makes it skimmable.

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?

No output schema exists, and the description tells the agent what persists, how long it takes, the timeout, and the date cap — the essentials for a long-running write. It leaves connection_context unexplained, the only meaningful omission for a 6-param tool.

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?

With 0% schema description coverage the description must carry the load, and it does for the four required params (UUID format, date YYYY-MM-DD) plus the optional selected_source_refs override semantics and an explicit 'use date_from/date_to not start_date/end_date' disambiguation. It omits the connection_context parameter present in the schema, so not full coverage.

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+resource+scope: 'Fetch and persist cohort rows for one app under one MMP connection.' This clearly separates it from siblings like mmp_save_cohort_config (config) and mmp_get_state (read-only state), and the 'Mirror of Meta MCP mmp_fetch_cohorts' note anchors intent.

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?

Provides explicit context ('treated as an explicit read refresh, never an onboarding side effect') and a concrete precondition (date range ≤ 31 days), which tells the agent when this is the right call. It doesn't name a specific alternative sibling tool to route to, so it stops short of a 5.

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