find_words

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses case/punctuation-insensitive matching, timecode format specifics including drop-frame behavior, the eos field as a cut-boundary signal, inclusion of activeSequence, and the fact that the call can operate against a restricted time window. This goes well beyond what the schema alone provides.

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 information-dense with no filler. It front-loads the core purpose, then adds return-value details, usage guidance, matching behavior, and result caveats—each 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?

Given the absence of an output schema, the description fully explains return values: startSec/endSec, timecodes, surrounding context, speaker, eos, and activeSequence. It also covers prerequisite conditions and provides an explicit comparison to get_transcript, making the tool self-sufficient for correct selection and 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?

Although schema coverage is 100%, the description adds meaningful semantics: multi-word queries match consecutive spoken words, startSec/endSec bound the sequence-time window, and maxMatches defaults to 8 with totalMatches reporting the full count. These details help the agent construct correct calls far beyond the raw parameter names.

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 a specific verb and resource: 'Search the active sequence's transcript for a word or phrase and get WORD-ACCURATE sequence times.' It also clearly differentiates itself from the sibling get_transcript by emphasizing word-level accuracy and comparing it to clicking a word in Premiere's Text panel.

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 explicitly tells the agent when to use this tool instead of an alternative: 'Use this to snap marker/cut points precisely instead of relying on get_transcript's sentence-level segment starts.' It also notes the prerequisite ('Requires transcribed clips, same as get_transcript') and describes optional time-window restriction, giving clear context for invocation.

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