Start Watch

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

With no annotations, the description carries the full load and does well: it discloses the auto-transcription side effect, that files are moved to a done directory, the default done path, the env-var override, and that out-of-allow-list paths cause rejection. It omits what happens if a watch is already running on the same folder or how to stop it (stop_watch).

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 short sentences, front-loaded with the core action and effect, then constraints, then the follow-up call. No filler and each sentence adds an actionable fact.

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?

For a one-parameter tool with an output schema (so return values need no explanation), the description covers purpose, side effects, directory constraints, and the results-retrieval path. It leaves minor gaps around duplicate/conflicting watches and error semantics.

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 baseline is 3, but the description adds real meaning for the single parameter: the folder must be inside the configured allow-list or the call is rejected, and it explains the related done-directory path and its override. That is more than the schema's path-format description provides.

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 (start watching), resource (a folder), and outcome (auto-transcribe new audio files), which cleanly separates it from stop_watch, get_watch_results, and one-shot transcribe_audio. An agent can identify the operation without opening the schema.

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 routes the agent forward explicitly ('Call get_watch_results() to retrieve completed transcriptions'), giving clear post-invocation context. It does not, however, state when to prefer this persistent watch over the sibling transcribe_audio for a single file, so the exclusion guidance is incomplete.

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