judge_video

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

With no annotations, the description carries the full burden and does add one genuinely useful trait: 'worthwatch calls no model here: you do the judging', which tells the agent this returns instruction material rather than a computed verdict. However, it never clarifies side effects — whether step 3 saves anything itself or merely instructs, and whether the call is read-only — which matters for a tool with a save_verdict sibling.

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?

Front-loaded with the core purpose and structured as a numbered breakdown, with no filler sentences. The nested colon-list is slightly dense but every clause carries information.

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?

Because there is no output schema, the description usefully tells the agent roughly what comes back (decision rules, write-up format, save instructions), which is strong. But it leaves the single input's format unspecified and the save behavior ambiguous, so it is not fully complete for a no-annotation tool.

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?

The single required parameter 'video' has 0% schema description coverage and the description adds nothing: it does not say whether the value is a URL, video ID, or title. This is the one field the agent must supply, and its format is undocumented in both places.

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 ('judge one video for the user') and enumerates the verdict outputs (YES, OPPORTUNITY, MAYBE, NO), so the agent knows exactly what the call produces. Sibling differentiation is partial: step 3 ('how to save it') overlaps with the save_verdict sibling, leaving it unclear which tool actually persists the result.

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 step 1/2/3 framing implies a workflow (judge, then write up, then save) and step 2's 'with the full transcript' hints the transcript should already exist, but no sibling is named and there is no explicit when-not or 'call get_transcript first' routing.

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