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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. Beyond that, the description discloses genuinely valuable behavior: this is a partial-update operation (only changed fields need to be sent) and it surfaces three non-obvious defaults (approval request on, strategy run start off, finish on). The main gap is that defaults are given for only 3 of 16 fields, leaving the agent to guess whether an omitted field reverts to a default or stays untouched.

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 with the invocation rule front-loaded, and no restating of the name or title. The trailing defaults fragment is slightly telegraphic and would read better as a single sentence, but nothing here is padding.

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?

An output schema exists, so return values need not be explained, but for a 16-parameter mutation tool with near-zero schema documentation the description leaves major questions open: the scope of a strategy-scoped versus global update, whether null differs from omission, and what the defaults are for the other thirteen flags. That is thin for a tool of this surface area.

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 6% – only strategy_id carries any description, and even that one is boilerplate. The description names just three of the sixteen parameters and explains the boolean typing generically; it never clarifies what triggers alert, journal, deepdive, screener, price-move, or acceleration notifications, nor whether email_notifications is a channel toggle or a master switch. With coverage this low, the description needed to compensate and does not.

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 states a specific verb and resource ("Update notification preferences") that an agent can immediately map to the sibling read tool get_notification_settings. It does not explicitly name that sibling or state the distinction, but the operation itself is unambiguous for a 16-field boolean settings object.

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?

"Pass only the fields to change" is a useful invocation rule that tells the agent to send a partial payload rather than a full settings object. However, there is no guidance on when to use this versus get_notification_settings, no mention that strategy_id scopes settings to a specific strategy versus global preferences, and no prerequisites or permission notes.

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