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

With no annotations, the description carries the full behavioral burden, and it does so well: it discloses that other lines are removed, which line survives, how texts are ordered, and the union window behavior. It stops short of describing error handling or the return value, but the mutation semantics are transparent.

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?

Two tightly packed sentences with no filler. The core purpose is front-loaded, and the constraints are presented in the second sentence without unnecessary repetition of schema details.

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?

Despite having no annotations or output schema, the description gives an agent everything needed to invoke it correctly: input expectations, merge behavior, outcome for non-surviving lines, and track-level preconditions. No critical operational information is missing.

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 coverage is 100%, so the baseline is 3. The description adds useful semantic detail beyond the schema, such as the requirement for at least two lines, the time-ordering of joined texts, and the same-clip-or-standalone constraint.

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 clearly states a specific action and resource: merging two or more caption lines into one, with precise behavior ('earliest line survives', 'time-ordered texts joined by spaces', 'others are removed'). It is easily distinguished from sibling tools like split_caption_line or add_caption_track.

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?

It gives clear operational context and explicit preconditions: all lines must share the same flavour and no other caption line may sit inside the merged span. It does not name alternatives or explicitly say when not to use this tool, but the conditions are concrete enough to guide selection.

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