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

Annotations cover the safety profile (readOnly=false, destructive=false, openWorld=false, all consistent with this being a local mutation), so the description's added value is the side effect: the agent gains the record_outcome tool plus a report-once-done instruction. The 'merged, never rebuilt' note also discloses mutation semantics. Minor tension: the schema's `units` entry says '(replaces)' while the description says merged, leaving the exact merge/replace boundary for the list unclear.

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, front-loaded with the core action and effect. The clipped fragment 'Merged, never rebuilt.' is terse to the point of ambiguity but costs no space; nothing is padded.

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 five-parameter mutation with no output schema, the description covers the key things an agent cannot read elsewhere: the downstream side effect on the agent and the merge-versus-rebuild behaviour. Remaining gaps (interaction of `clear` with `units`, permission requirements) are modest and partly covered by schema field descriptions.

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 100%, so the baseline is 3, and the description genuinely adds meaning beyond it by explaining what `node` and `when` mean in practice — the workflow node the outcome fires on and reporting only once the work is actually done. ROI parameters (minutes_saved, value_per_unit) are left entirely to the schema, which is acceptable given full coverage.

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: choosing which outcomes an agent reports, and names the downstream mechanism (record_outcome tool plus instruction). It does not differentiate itself from siblings like define_outcome_unit or set_goals, so an agent must infer the boundary between defining an outcome unit and assigning it to an agent.

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?

Usage is implied rather than stated: describing the resulting agent behaviour makes it clear this is the wiring step, but there is no explicit when-to-use, no prerequisite (e.g. define the unit first via define_outcome_unit), and no routing away from set_goals or update_agent.

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