Get event

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds real behavioral context by disclosing the two id namespaces, the return shape (message and payload), and the services:read vs account:read authorization split. It does not discuss pagination or retention, which keeps it from a 5.

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 purpose and state list, then the accepted id forms, then permissions — a logical order. Efficient overall, though the 'proccessing' typo and some redundancy in the long action list detract slightly.

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 single-parameter read tool with no output schema, the description covers purpose, id semantics, return contents, and authorization needs. An agent has everything required to call it correctly.

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 100% and the schema type pattern already covers the id, but the description adds meaning beyond it by mapping which specific operations emit an event id versus a UUID. That mapping is genuinely value-adding over the schema's generic 'returned by the action' phrasing.

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: 'Read the state of an asynchronous action,' and enumerates the possible states (created, processing, completed, error). An agent can immediately distinguish this polling tool from sibling wait_for_event and from the mutation tools that generate events.

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?

Explains exactly which ids to supply and where they originate (start/stop/restart/console/suspend/resume return `event`; hostname/password/SSH-key/reinstall/IPv6/etc. return `noty`), plus the required read permissions per event class. It does not explicitly name the alternative (wait_for_event) or state when not to use it, so it stops short of a full 5.

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