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

Annotations already declare the safety profile (destructiveHint=true, readOnlyHint=false), so the burden is reduced. The description usefully adds two behavioral facts beyond the annotations: a partial-update semantic ('only supplied fields are forwarded') and a failure mode ('returns mmp_not_enabled while MMP is not enabled'). It does not explain what existing config is overwritten or whether the save is reversible, which for a destructive tool is a meaningful remaining 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?

Three short sentences, purpose front-loaded, each carrying a distinct fact (what it does, forwarding semantics, error return). No filler or repetition.

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 13-parameter mutation tool with 0% schema coverage and no output schema, the description is under-specified. It does compensate slightly by disclosing the mmp_not_enabled return, which is useful without an output schema, but it never explains what the parameters configure or what a save replaces.

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 13 parameters, so the description must carry the parameter burden and does not. Nothing explains kpis, groupings, cohort_type, period_filters, min_cohort_size, aggregation_type, connection_context, or the currency/timezone flags. The only relevant hint is 'only supplied fields are forwarded', which does not map to any specific field.

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 (save) and resource (cohort fetch parameters) scoped to 'one MMP app on the Meta-owned MMP service'. This is clearly a write operation and distinguishes it from read siblings like mmp_fetch_cohorts and mmp_get_state. It stops short of naming an alternative explicitly, so it is clear but not sibling-differentiating at the highest level.

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?

No when-to-use, when-not-to-use, or alternative-tool guidance is given. The agent must infer from the name alone whether to call this vs mmp_fetch_cohorts or mmp_refresh_connection. There is a note about partial forwarding, but nothing that routes the agent between tools.

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