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

Annotations only declare readOnlyHint=false; the description adds substantial context beyond that: the three refusal codes (NEEDS_RULING, RULING_CONDITION_NOT_MET, CLAIMED_APPROVAL_NOT_HUMAN), the per-copy attempt limit, the structured-fields-only constraint, and the fact that Atlas records its own fixed output. This is exactly the behavioral disclosure a mutation tool needs.

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 gating rule (refused before ruling, allowed inside ruling) is front-loaded, followed by the failure modes and the call-format constraint. It is dense and slightly run-on, but nearly every clause carries operational information and none is pure filler.

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 7-parameter mutation tool with no output schema, the description covers the decision gate, the refusal taxonomy, the attempt limit, and where to obtain valid arguments. The only minor gap is that the actual return payload is only alluded to ('Atlas records its own fixed output') rather than described.

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 already 86%, so the baseline is 3. The description goes further by showing a concrete argument pattern ('use: "forecast" with shown_with: ["panel_b"]') and by telling the agent that the ruling reply's settle_call supplies the exact arguments, which is actionable guidance the schema alone does not provide.

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 gives a concrete verb+resource ('set the Q4 planning number') and tightly scopes it to 'Practice mode, Consumer Pulse copy only (Magistrate demo, steps 2 and 5)', which clearly separates it from the other pulse_* siblings. The phrasing 'ask to set' is slightly indirect, but an agent can identify the action and its boundaries without opening the 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 states the conditions of use explicitly: refused with NEEDS_RULING before the Magistrate's ruling, and allowed only inside the ruling afterwards (with an example of the required use/shown_with combination). It does not name an alternative tool for the out-of-scope case, but the gating conditions are unusually well specified.

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