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

Annotations already declare read-only/idempotent/non-destructive behavior; the description adds non-blocking wait semantics, the 20s/100 caps, terminal flag meaning, and pagination via next_from_seq. 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?

Every element earns its place: behavior is front-loaded, followed by the example, return shape, caps, and termination semantics. There is no fluff, tautology, or repetition of the title.

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-only tool with no output schema, the description covers input semantics, return fields, continuation, caps, and terminal behavior. An agent has what it needs to select and call the tool 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 0%, so the description carries the burden. It compensates by explaining from_seq as a continuation token, max_events and wait_seconds as stop conditions, their caps, and an example mapping all four parameters. It does not state defaults when optional parameters are omitted, leaving a minor gap.

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?

Description opens with a specific action ('Opens the run's event stream'), names the resource (run event log), and defines its output behavior. The title and phrase 'watch a build without polling' clearly distinguish it from status/query/get tools.

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?

Explicitly frames the tool as the way to watch a build without polling and explains the continuation pattern ('Call it again with from_seq set to next_from_seq'). It does not name sibling alternatives or state when not to use it, so it stops short of a 5.

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