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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false). The description adds substantial behavior beyond them: synchronous/slow latency, page caps (1000 rows / 256KiB), the oversized_row whole-row exception, the truncated flag driving continuation, and the mmp_not_enabled error condition. This is exactly the extra context annotations don't provide.

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?

Three dense sentences with the core purpose front-loaded and pagination/latency/error details packed efficiently. No filler, though the pagination sentence is heavy and could be marginally clearer.

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?

With no output schema, the description takes on return-value disclosure and does so credibly (paging limits, oversized_row, truncated, next_cursor, error code). Combined with the latency warning, an agent has enough to invoke and continue correctly, with the main gap being unexplained non-cursor parameters.

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% across 7 parameters, so the description carries the full burden. It explains cursor/next_cursor pagination semantics well, but says nothing about connection_id, app_ref, date_from, date_to, connection_context, or selected_source_refs, leaving most parameters undocumented in both schema and prose.

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 states a specific verb (fetch and store) and resource (one cohort window for one MMP app on the Meta-owned MMP service), and it clarifies scope ('one cohort window for one MMP app') which separates it from config/state siblings like mmp_save_cohort_config or mmp_get_state. It does not explicitly name alternatives, so it falls just short of the top mark.

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?

It gives the pagination follow-up rule ('when truncated=true call again with next_cursor as cursor') and warns the call is 'Synchronous and slow', which is useful timing context. However, it offers no guidance on when to choose this tool over sibling MMP tools or what prerequisites (e.g. enabled MMP) look like beyond the error note.

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