host_preset_update

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

With no annotations, the description carries the full burden and does well: it discloses staging semantics ("Changes stay unsaved"), required auth-ish context (current session ID, UUID hex request ID), the fact that native dialogs are not suppressed, and the non-idempotent timeout behavior. Missing only permission/scope details and whether a separate commit call exists.

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?

Five short lines, front-loaded with the action, then the required inputs, then the failure-mode caveat. No filler sentences; only the phrase "official host transaction API" is somewhat jargon-heavy.

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, and the transactional behavior is well covered. But for a 7-parameter, 5-required mutation with 0% schema documentation, the description should explain at minimum what `kind`, `changes`, and `slot` mean; that gap keeps it at minimum-viable.

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 0% across 7 parameters, yet the description only characterizes two of them (session_id as current session, request_id as a UUID hex). The required parameters kind, preset_name, and changes — plus slot and timeout_seconds — get no meaning, format, or constraint hints, so the schema gap is largely uncompensated.

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 verb phrase "Stage/commit live settings through the official host transaction API" signals a transactional write, but it never says the resource is a *preset* (the name says preset_update, the text says settings), leaving ambiguity against siblings like settings_write, project_settings_write, and host_preset_read. An agent can infer it mutates host state but not precisely which 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?

There is real guidance on the retry path ("A timeout is indeterminate: query the receipt instead of repeating the edit"), which implicitly routes to host_request_status, but no explicit statement of when to use this versus settings_write / project_settings_write, nor any stated prerequisites beyond the session/request IDs.

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