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

With no annotations, the description carries the full burden and does a good job: it explains the polling model ('polls the batch's aggregate status periodically'), the per-tick notification behavior, and the exact termination condition, naming both terminal statuses (completed, completed_with_failures). It stops short of stating the poll interval, error/timeout behavior, or whether the call blocks until completion, which leaves some uncertainty about calling semantics.

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?

Three clauses, each earning its place: the core action, the observable lifecycle, and the routing alternative. Front-loaded with the streaming behavior and no redundant restatement of the name or 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 single-parameter streaming tool with no annotations and no output schema, the description covers the essential contract: what triggers it, what it emits per tick, and when it closes. It omits the shape of the progress notification payload and the polling cadence, so an agent knows the lifecycle but not the payload it will receive.

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% and batchId has no type or format guidance, but the description supplies the key semantic link: the ID refers to a batch produced by build_batch, which tells the agent where the value comes from. No format, validation, or lookup hint is added, so it is adequate but not generous.

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 ('Stream live progress for a batch') and immediately ties the resource to its origin ('submitted via build_batch'), which identifies the correct input domain. It also distinguishes itself from the sibling get_batch by contrasting live streaming with a point-in-time snapshot.

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 alternative and the condition that selects it: 'Call get_batch instead for a single point-in-time snapshot.' The streaming use case (watching progress until a terminal state) is stated directly, so an agent can choose between the two without guessing.

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