stream_poll

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds useful behavioral context by mentioning buffered samples and dropped-sample detection. However, it does not clarify whether polling consumes the buffer, whether it blocks, or how dropped samples are indicated, leaving meaningful behavioral gaps.

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?

The description is a single efficient sentence with no wasted words. It front-loads the core action and adds the dropped-sample detection as useful secondary context.

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 simple read-only polling tool with clear annotations and no output schema, the description conveys enough to understand the basic call: it reads buffered samples after a sequence and can detect dropped samples. Minor gaps remain around blocking behavior and return format, but overall it is adequate.

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 50%: the `id` parameter is documented in the schema, while `after_sequence` is not. The description compensates partially by explaining that samples are read after a sequence number, but it does not specify the format or expected relationship to stream_start, nor does it clarify acceptable values beyond the schema's minimum of 0.

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?

The description states a specific verb ('Read') and resource ('buffered samples') with a clear scope ('after a sequence number') and an additional behavior ('detect dropped samples'). It does not explicitly differentiate itself from siblings like stream_list or stream_start, but its polling purpose is 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?

The description implies usage (polling a stream for buffered samples after a given sequence), but it provides no explicit guidance on when to use this tool versus stream_list, stream_start, or stream_stop, nor does it mention polling intervals or error handling.

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