audio_ingest

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'extract semantic memory' and a configuration requirement, but it does not disclose side effects (e.g., whether audio is stored, deleted, or processed), permissions needed, or the return format. The description is vague about the tool's operational behavior, which is a significant gap given the lack of annotations.

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 concise: two sentences, with the main action front-loaded. The 'NEW (Audio Intelligence)' prefix is a minor label but not wasteful. Every sentence contributes either purpose or a prerequisite, making it appropriately sized without unnecessary fluff.

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?

With no annotations, no output schema, and an incomplete parameter schema, the description must provide more context. It states the tool's purpose and a config requirement, but it does not explain return values, what 'extract semantic memory' entails, or how the parameters interact. This leaves significant gaps for an agent to correctly invoke and interpret the tool, especially with 4 parameters and a nested metadata object.

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 only 25% (only audio_url has a description), so the description must compensate for the other parameters. The description lists audio types (calls, voice notes, podcasts, music) that map to the source_type enum, but it does not explain audio_url, customer_id, or metadata fields. This offers minimal additional meaning beyond the schema, failing to fill the coverage gap.

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's purpose with a specific verb ('Ingest audio') and resource ('calls, voice notes, podcasts, music') and an outcome ('extract semantic memory'). It does not explicitly differentiate from sibling tools like audio_recall or remember, but the term 'ingest' and 'audio-intelligence layer' imply a distinctive ingestion-focused role, which is clear enough.

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 implies usage for ingesting audio into semantic memory, and it provides a prerequisite (BLUECOLUMN_API_URL pointing at the BlueColumn API). However, it does not explicitly state when to use this tool vs alternatives (e.g., audio_recall for retrieval), or when not to use it. The guidance is mostly implied rather than explicit.

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