events_read

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context: events are 'bounded', response is a 'legacy array', and the stream is 'shared per-session'. It also notes that events_page carries metadata this tool lacks. No contradiction with annotations.

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?

Two short sentences with no filler. The core purpose and scoping are front-loaded, followed by the sibling preference in the second sentence. Every word earns its place.

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 read tool with no output schema and 0% parameter coverage, the description explains the core purpose and response type but leaves parameter semantics unaddressed. An agent would need to infer how limit, afterSequence, provider, and nativeId interact with the stream. The annotations cover safety and the sibling pointer helps, but the description does not fully equip the agent to call it correctly for nuanced use cases.

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 description coverage is 0%, so the description must compensate for parameters provider, nativeId, limit, timeoutMs, and afterSequence. It provides only a generic 'bounded' hint and response format, with no explanation of how these parameters control the read, what afterSequence does, or how provider/nativeId identify the stream. Marginal value over the schema.

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 ('Read'), resource ('bounded native events'), scope ('one shared per-session stream'), and response format ('legacy array response'). Explicitly names events_page as the preferred alternative for reconnect/gap metadata, making the distinction from the sibling tool immediately clear.

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?

Clearly identifies events_page as the alternative when reconnect/gap metadata is needed, implying this tool is for simpler reads without that requirement. However, it does not explicitly state when-not conditions or prerequisites such as how to identify the session stream.

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