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

With no annotations provided, the description fully discloses behavior: it states the call is immediate, affects the next scheduled pull, silently returns zero rows for invalid kpis, and does not advertise a mutation receipt. It also explains that unset optional fields leave existing values unchanged. This covers the key behavioral traits an agent needs to know.

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 well-structured: opening purpose, behavioral notes, required params, optional fields, and an example. Every sentence adds value, and the most critical information (purpose and immediacy) is front-loaded. It is detailed but not verbose.

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?

Given the complexity (12 params, no output schema, no annotations), the description covers everything needed: prerequisites, parameter semantics, behavioral expectations, and a concrete example. It even sets expectations about the lack of a receipt. An agent can call this tool correctly without additional documentation.

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 compensate. It does: it lists required parameters with types and examples (connection_id as UUID from mmp_get_state, app_ref with Android/iOS examples), explains optional fields with types (list[str], list[int], boolean), and clarifies the 'unset = leave existing value alone' semantics. A full example call is provided.

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 clearly states the tool's purpose: 'Save one cohort config for a specific app under one MMP connection.' It uses a specific verb (save) and resource (cohort config) and distinguishes it from siblings like mmp_get_state or mmp_fetch_cohorts. It also labels it as WRITE and IMMEDIATE, making its role unambiguous.

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 explicit usage guidance: 'Call only for an explicit user-requested config change.' It also gives a clear prerequisite: 'call mmp_get_state first and inspect each metadata row's event_mappings / mapped_events for valid event names.' This tells the agent exactly when and how to prepare, and it warns against misuse.

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