capture_read

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

Adds significant non-obvious behavior beyond the readOnlyHint annotation: items carry a `live` flag whose false/true meanings are explained (replay versus live session data). It also exposes the need to monitor stream_state, which is exactly the kind of runtime behavior an agent needs to know to use the tool correctly.

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 short, dense sentences with no filler. The core action is front-loaded, then operational instructions, then the crucial live/replay semantics. Every sentence 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?

Covers the essential stateful behavior: sequencing, reconnection checking, and replay semantics. The presence of an output schema likely provides where last_seq and stream_state appear, so the description does not need to repeat that. Slight gap: limit is never mentioned, but its meaning is fairly self-evident.

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. It fully explains since_seq semantics ('seq > since_seq', pass last_seq back), which is the least obvious parameter. However, session_id and limit are left to inference from their names/context and are not explicitly described.

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 captured items with seq > since_seq.' This clearly identifies what the tool does and distinguishes it from capture lifecycle tools like capture_start/capture_stop and capture_list. The inclusion of the sequencing detail makes the purpose unambiguous.

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?

Provides explicit operational guidance: remember last_seq and pass it back next time, and check stream_state for reconnects. This tells the agent how to paginate and handle reconnections. It does not explicitly contrast with alternatives, but the stream/read context is clear enough.

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