capture

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

With no annotations, the description carries the full load and does disclose two meaningful behaviors: results are persisted under a capture_id, and the return is per-channel statistics (edges, pulse widths, rough frequency), never the raw samples. That prevents an agent from expecting raw data. It still omits hardware/permission needs, backend selection consequences, and failure modes, keeping it short of a 5.

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 tight sentences, front-loaded with the action and persistence, followed by return shape and practical advice. No filler and nothing redundant.

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?

The description usefully compensates for the missing output schema by describing return contents, and it hints at cost with 'short window first'. But for a 7-parameter acquisition tool with no annotations and a nested trigger object, leaving backend/device/trigger semantics entirely unexplained is a real gap for correct invocation.

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% across 7 parameters, including a nested trigger object and a backend enum (mock/sigrok/dslab) whose meaning is critical to invocation. The description explains none of them, so an agent gets no help interpreting device vs backend, trigger semantics, or sensible sample_rate/duration values.

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 ('Capture digital channels') and adds the persistence effect ('persist them under a capture_id'). It implicitly distinguishes itself from analysis siblings like analyze_window and decode_uart by being the acquisition step, but it never names a sibling explicitly.

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?

'Prefer a short window first' gives one piece of tactical advice, which is more than nothing. However, it never says when to choose this over list_captures (does capture create a new one?), nor when to use a trigger or which backend to pick, so guidance is implied rather than stated.

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