ingest_transcript_results

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

Annotations already declare `destructiveHint: true` (modifying state) and `readOnlyHint: false`. The description adds crucial context: 'Nothing is auto-confirmed', indicating the operation is safe in that it creates reviewable candidates without automatic confirmation. This adds transparency beyond 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?

Two sentences, no redundant words. The first sentence states the core action, the second adds a critical behavioral qualifier. Perfectly front-loaded and efficient.

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 two parameters, the description covers the primary purpose and a key behavioral trait (no auto-confirm). It does not detail return values or prerequisites (e.g., source_id must exist), but for a pipeline tool it is reasonably complete.

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% with clear descriptions for both parameters. The description adds minimal extra meaning beyond the schema, simply indicating the role of the extraction JSON as 'model-produced'. Baseline 3 is appropriate as the schema already documents adequately.

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?

Description clearly states the verb ('parse' and 'ingest') and the resource ('model-produced extraction JSON' into 'reviewable Decision Graph candidates'). It distinguishes from siblings like `ingest_transcript` by specifying the input is extraction JSON from a model, not raw transcript.

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 context: when a model produces extraction JSON that needs to be turned into reviewable candidates. However, it does not explicitly state when NOT to use the tool or mention alternatives like `ingest_transcript`. The context of siblings provides some implicit differentiation.

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