kernel_places_set

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

With no annotations, the description carries the full burden. It delivers one genuinely non-obvious behavioral fact — a hand-set place is never overwritten by a sync — which materially affects how an agent treats this data. It does not disclose the most important mutation semantics, however: whether setting a location for an existing item overwrites a prior value, whether the call is idempotent, what happens on an unknown ref_id, or what permissions are needed.

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?

Four short sentences, front-loaded with the core action, then the two modes, then the coordinate input forms, then the persistence guarantee. Nearly every clause earns its place; the only mild friction is that the 'Takes lat/lng or a map link' clause is buried after the mode explanation rather than adjacent to the input discussion.

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. For a 7-parameter mutation tool with zero annotations, though, the definition should say more about update-versus-create behavior and the undocumented 'address' field. The sync-immunity note is valuable but does not fully cover the operational risk surface of a write tool.

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 only 29%, so the description must compensate and largely does: it explains kind's role and the manual variant, defines ref_id ('The item's id; leave out for a new place of your own'), ties name to the manual kind, and clarifies that link is an alternative to lat/lng ('a map link or lat, lng'). Only the 'address' parameter is left entirely unexplained by both schema and description.

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 concrete verb and resource ('Set where something is, by hand') and immediately splits the operation into two distinct modes: item placement via 'kind + ref_id' and manual place creation via 'kind \'manual\' with a name'. It distinguishes behavior from the sync path ('never overwritten by a sync') without naming a sibling tool, so an agent understands the intent but gets no explicit routing to kernel_places_list / kernel_places_search / kernel_places_sync.

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?

Clear conditional branching is provided: use item kinds with ref_id for events/trips/accommodations/activities, and 'manual' with a name for the user's own places like home or office. What is missing is exclusion guidance — when not to call this (e.g. when a place already exists and should be synced instead) and any prerequisite about which id namespace ref_id draws from.

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