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

Adds substantial behavior beyond the annotations: the first call is a no-op validation pass that returns a summary and a confirm_token, unknown fields are refused by name, and the real mutation only happens on the confirmed second call. That directly explains how a destructive, non-idempotent operation (destructiveHint=true, idempotentHint=false) is made safe, plus the auth scope requirement. No annotation is contradicted.

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?

Short, front-loaded and dense: purpose, permission, then the call protocol in the order the agent needs it. Telegraphic phrasing ("Two calls.") is efficient rather than confusing. A little more structure on the field-scope point would have avoided the one ambiguity without adding bulk.

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?

No output schema exists, and the description compensates by naming what the first call returns (summary plus confirm_token), which is exactly what an agent needs to drive the confirmation loop. It also covers auth and error behavior (unknown fields refused by name). The one missing piece is the set of changeable fields on a tool with an open additionalProperties schema.

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?

The confirm_token meaning is restated and slightly enriched ("the confirm_token the first call answered", plus "same arguments"), matching the 50% schema coverage. The significant gap is that the schema exposes only `id` and `confirm_token` with additionalProperties=true, and the description never enumerates which busy-block fields may be changed — it only hints that some fields exist and others are refused. With half the parameters undocumented, this is baseline rather than compensating.

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 ("Change a busy block"), which separates it from create_busy_block, delete_busy_block, restore_busy_block and skip_busy_occurrence in the sibling list. It also immediately flags the two-phase nature, so an agent knows this is not a single-shot mutation. It stops short of naming the sibling operations or the field set, so it is clear but not fully differentiated.

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?

Gives explicit operating context: requires the `calendar:write` scope, and prescribes an exact two-step procedure (first call validates only, show the summary to the person, only then repeat with confirm_token). This is strong procedural guidance. It does not offer alternatives (e.g. create vs change vs restore busy block, or update_live_event), so the when-to-use-this-vs-siblings dimension is only implied by the name.

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