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

Annotations only say it is a non-read-only, non-destructive, closed-world write. The description adds genuinely new behavioral facts: the operation is synchronous, it should only run on explicit user request, and it returns mmp_not_enabled when MMP is not enabled for the tenant. That error-state disclosure is useful context an agent could not get from the annotations.

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 short, front-loaded clauses with no filler; the verb and resource come first and the constraints follow. The phrasing "Refresh one MMP connection metadata" is slightly clipped but still efficient.

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 2-parameter write tool with no output schema and no parameter documentation, the description covers the mutation semantics and one error code but leaves both parameters and any success response undefined. Adequate at the top level, with a clear gap at the parameter level.

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% for both parameters, so the description carries the full burden and fails to explain connection_id or the connection_context format (mctx_v1_...). "Refresh one MMP connection metadata" only weakly implies that connection_id selects the target; connection_context is entirely unexplained.

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 (Refresh) and a specific resource (one MMP connection metadata on the Meta-owned MMP service), which clearly separates it from siblings like mmp_get_state, mmp_delete_connection, or mmp_save_cohort_config. It does not name an alternative sibling explicitly, so it stops short of a 5.

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?

"Call only on explicit user request" gives a real gating condition for when to invoke it, which is more than most siblings offer. It does not, however, contrast this tool against related ones such as mmp_get_state or mmp_fetch_cohorts, so the when-not/alternatives half is missing.

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