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

Annotations only declare destructiveHint=false, so the description carries most of the burden and does deliver real behavioral detail: what 'on' does (immediate fill at the security's last price) versus 'off' (orders acknowledged and queued). It does not cover persistence of the setting, required session state, or idempotency, leaving some gaps.

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 tightly packed sentences with zero filler, front-loading the purpose before the mode definitions. Every clause earns its place by defining behavior that the structured fields do not.

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 simple two-parameter setter with no output schema and sparse annotations, the description covers what an agent needs to call it: the effect of each flag value and the default. Prerequisite session state and whether the setting persists are not addressed, but the core is complete.

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 effectively explains the semantics of 'enabled' (on = immediate fill, off = pending), but says nothing about 'sessionId' beyond the implicit name. Since the enabled meaning maps well to the schema but sessionId is untouched, this is adequate but partial.

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 and resource ('Turn automatic fills on or off for a sandbox session'), which is unambiguous and clearly distinct from sibling tools like sandbox_act_on_order and sandbox_send_order. An agent can identify the operation 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?

Explains the two modes and explicitly notes that 'Off' is the default and that orders then 'wait for sandbox_act_on_order', effectively naming the alternative tool and the state that selects it. It stops short of an explicit 'use this when...' routing sentence, so it is clear context rather than full when/when-not guidance.

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