start_show

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The tool performs a show-starting mutation, but the description doesn't disclose whether this affects existing state destructively, whether it requires OBS to be connected, what happens to the previous show state if one is active, whether it can fail mid-opening, or what triggers are involved. 'Initializes state' is vague about what state gets reset or overwritten. Given zero annotation coverage for what appears to be a significant state-mutating operation, this is a notable gap.

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 brief—two sentences, zero wasted words. It front-loads the key verb and purpose. However, it's arguably under-specified rather than efficiently concise; the brevity comes at the cost of missing behavioral and usage context. Still, as written, it's structurally clean and scannable.

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?

This is a show-lifecycle mutation tool with no output schema, no annotations, and moderately documented parameters. An AI agent needs to know what 'initializes state' entails, whether re-invoking start_show mid-show resets everything, how it interacts with the many siblings (get_current_show_state, set_safety_mode, reconnect_obs), and what success/failure looks like. The description is too thin to support confident, correct invocation in a complex show-control context.

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%, with show_template_id and start_segment_id documented in the schema. The description mentions 'loads show template' which maps to show_template_id, adding some context about its role. However, it does not explain the behavior of the 'options' object (skip_opening vs. start_segment_id interaction—are they mutually exclusive? what takes precedence?), nor the default template behavior. The description adds marginal value over the schema for half the parameters but leaves the options sub-object semantics under-explained.

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 'Start a show and execute opening sequence. Loads show template and initializes state.' This uses a clear verb (start) and resource (show), and hints at what happens (loads template, initializes state). However, it doesn't explicitly distinguish from the sibling 'end_show' which is the obvious counterpart, nor does it clarify how it relates to 'switch_segment' or 'extend_segment' which are all show-lifecycle tools. The purpose is clear but sibling differentiation is weak.

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?

No explicit when-to-use or when-not-to-use guidance is given. There is no mention of when start_show is appropriate vs. alternative tools like switch_segment or when it's not appropriate. The description doesn't state prerequisites (e.g., does the show need to be fully configured first? must OBS be connected via the reconnect_obs sibling? should safety_mode be set?). Usage context is essentially absent.

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