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

Annotations already declare not read-only, not open-world, not destructive, so the safety profile is partly covered. The description adds meaningful behavior beyond that: partial-update semantics ('only the fields given change') and a scope guarantee ('never move money'), which prevents the agent from assuming financial side effects.

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?

Two tight sentences with the upsert behavior front-loaded and the scope disclaimer second. No filler, and the most decision-relevant facts (create vs update, partial update) come first.

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 mutation tool with no output schema and full schema coverage, the description supplies the upsert model, partial-update rule, and non-financial scope. It stops short of noting permission requirements or conflict/error behavior, but that is a minor gap.

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 coverage is 100%, so the baseline is 3, but the description earns a bump by clarifying the semantics that matter most for the params: which fields change on update and that updates are field-selective rather than replacing the whole unit. The 'code' key's dual create/update role is also explained outside the schema.

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 precise verb pair (create or update on upsert) plus the resource ('organization outcome unit') and the key ('when the code exists'). This cleanly separates it from siblings like list_outcome_units and set_agent_outcomes without the agent needing to open a schema.

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 implies usage by explaining the upsert trigger ('or update it when the code exists'), which tells the agent this is the single entry point for both create and edit. However, it never names an alternative tool or states when this should not be used (e.g., versus set_goals/set_agent_outcomes), so guidance stays implicit.

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