enrich_window

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

With no annotations, the description carries the full burden. It discloses idempotency (skips already-transcribed) and that it no longer touches images. It does not cover rate limits, auth needs, or error conditions, but the key behaviors 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?

The description is well-structured with a clear opening sentence, idempotent note, important caveat about images, and a enumerated workflow. It is concise but every sentence adds value, though the workflow could be slightly tighter.

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 no output schema and only 3 parameters, the description provides good context but leaves gaps: 'maxItems' and 'concurrency' are undocumented, and there is no mention of error handling or prerequisites (e.g., linked account). The workflow is helpful but incomplete for complex scenarios.

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 0%, so the description must compensate. It explains the 'hours' parameter ('last N hours') but does not explain 'maxItems' or 'concurrency' explicitly. While 'concurrency' might be inferred from context, the agent gets incomplete parameter guidance.

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 the tool does voice-only enrichment by downloading and transcribing voice notes via OpenAI Whisper. It explicitly contrasts with image processing, distinguishing it from siblings like get_image and set_description.

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 description provides explicit guidance: it is for voice enrichment only, and provides a step-by-step workflow (1) call enrich_window, (2) call get_image and set_description for images, (3) call get_recent_messages to write briefs. It also mentions that image analysis is done by Claude via get_image, clearly separating responsibilities.

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