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

Annotations already declare readOnly=false, idempotent=true, destructive=false, so the safety profile is covered. The description adds genuinely new behavioral facts: partial-update semantics, an account/consent prerequisite, and the fact that responses include source/freshness metadata. It stops short of explaining how nullable fields (e.g. boatId) are cleared or what happens to unmentioned nested keys.

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 lines, front-loaded with the operation and scope, followed by the permission requirement and then units/source notes. Nothing is padded, though the 'Units: ft, kt, s, F, mi' fragment is telegraphic and would benefit from mapping units to their fields.

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 a deeply nested body, no output schema, and 0% parameter documentation, the description covers purpose, auth, units, and return provenance. It does not cover how to reset nullable fields or how nested objects merge, which an agent would need before issuing a correct partial update; annotations at least carry the safety and idempotency profile.

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% and the single 'body' parameter hides roughly fifteen nested fields (theme, view, alerts.*, draftFt, cruiseKt, homeSpotIds, etc.). The description compensates only partially, supplying units (ft, kt, s, F, mi) and a direction convention ('directions FROM') that the schema lacks, but giving no per-field meaning for theme, view, alerts, or the null/clear semantics for nullable fields.

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 sentence 'Update only specified vessel or preference fields' gives a clear verb (update) plus resource scope (vessel/preference fields), and the partial-update wording ('only specified') distinguishes it from a full replace. It does not name the nearest siblings (get_my_settings, update_my_notification_settings), so an agent must infer the boundary from the scope phrase alone.

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?

There is no when-to-use guidance, no mention of the sibling update_my_notification_settings that shares the update surface, and no stated preconditions beyond the account requirement. 'Update only specified fields' implies partial-update usage but never says when this tool is preferred over its alternatives.

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