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

Goes well past the annotations: it discloses that the preview changes nothing and returns a changeId, before/after, notification count and notice text; that pass holders are notified unless `notify` is false; that non-organizers are refused with the reason surfaced verbatim; and that a personal connector token is required. This is consistent with destructiveHint=true and idempotentHint=true rather than contradicting them.

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?

Front-loads the core action, then the preview protocol, then identity resolution, then permission and auth — a sensible order for an agent to consume. It is dense with semicolon-chained clauses, so each line does earn its place, but the run-on final sentences cost some readability.

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 an 11-parameter, destructive, token-gated mutation with a required confirmation handshake, the description covers workflow, safety, error handling and identity resolution. Return values are covered by the existing output schema, so nothing an agent needs to call this correctly is missing.

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 already 100%, so the baseline is 3, but the description adds real semantics the schema cannot express: the `confirm`/`changeId` pairing, the effect of `notify` (quiet vs. pass-holder notification), and the interplay between `sessionId` and `sessionTitle` when disambiguation fails. It does not explain how `at`, `date`, `start` and `end` combine, which is where the remaining ambiguity sits.

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 ('Moves one session on the agenda of an event') along with the exact mutation surface (start time or room) and the authorization boundary ('an event the person organizes'). The concrete example ('push the keynote to 4:30 PM') removes any doubt about intent, and it is clearly distinguishable from siblings like event_session_add, event_session_cancel and event_session_rename.

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 an explicit two-step protocol: first call without `confirm` for a preview, then re-call with `confirm: true` plus the returned `changeId` only after the organizer agrees. It also names the required alternative when the session reference is ambiguous ('on AMBIGUOUS or NO_SUCH_SESSION read the candidates back and ask') and the fallback naming path (sessionId or title).

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