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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=true), so the bar is lower, and the description still adds real signal: the write is IMMEDIATE and drives the next scheduled cohort pull, unset fields are left alone, a bad kpi silently returns zero rows, and 'no mutation receipt is advertised.' It stops short of describing what existing settings get overwritten or auth requirements.

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-loads the WRITE/immediacy warning, then required, then optional, then a concrete example. Sized sensibly for 13 undocumented parameters; only minor redundancy in the user-requested-change / no-receipt sentence pair.

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 destructive 13-param mutation with no output schema, the definition covers prerequisites, partial-update semantics, a silent-failure trap, and a worked example. Gaps remain on the undocumented connection_context parameter and on what a failed or rejected save looks like.

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 carries the burden and only partially compensates: it identifies both required params with UUID/format examples and lists the optional fields with types plus the 'unset = leave existing value alone' default semantics. It gives no meaning for cohort_type, aggregation_type, period_filters, or min_cohort_size, and omits connection_context entirely.

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: 'Save one cohort config for a specific app under one MMP connection.' It is clearly separable from siblings like mmp_get_state (discovery), mmp_fetch_cohorts (read), and mmp_delete_connection.

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?

Explicit when-to-use ('Call only for an explicit user-requested config change'), prerequisite ordering ('call mmp_get_state first and inspect each metadata row's event_mappings / mapped_events'), and a named alternative for the discovery step. Not left to inference.

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