ingest_voice

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

With no annotations, the description must fully disclose behavior. It explains the conversion process and output structure, but does not mention side effects (e.g., whether data is persisted) or auth requirements. It implies storage in context memory but lacks explicit mutation semantics.

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 summary line, detailed explanation, explicit argument list, and return value description. It is concise with no redundant content, effectively communicating the tool's purpose and usage.

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?

The tool has two simple parameters and a clear output schema described. The description covers input, transformation, and output. It mentions the types of extracted information (decisions, actions, etc.) and return structure. However, it does not address error conditions or limitations.

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?

The description adds substantial meaning to both parameters. For 'transcript', it specifies it is the full transcript text; for 'source', it provides an example identifier. Since the schema has no descriptions, this compensation is crucial and effectively clarifies each parameter's role.

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 function: 'Ingest a voice/meeting transcript into the context memory.' It specifies the input type and the output structure, making it distinct from sibling ingest tools like ingest_diagram and ingest_diff. The verb 'ingest' and resource 'voice/meeting transcript' are specific.

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 does not provide explicit guidance on when to use this tool versus alternatives. While its purpose implies usage for voice/meeting transcripts, it does not mention exclusions or compare with sibling tools like remember_fragment or ingest_diff, leaving the agent to infer context.

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