start_shadow_index

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

The description explicitly claims 'Idempotent (resumable)', but the annotations declare idempotentHint=false — a direct contradiction on the same behavioral property, which could cause an agent to assume repeated invocations are no-ops. Although the description valuably notes the active model is untouched and search stays live, the explicit conflict with structured metadata forces a 1.

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, each carrying a distinct fact (what it does, safety during run, resumability, next step). The core action is front-loaded and there is no filler.

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 three-parameter mutation tool with no output schema and 0% schema description coverage, the description omits all parameter semantics and does not describe progress reporting or error behavior. It covers the operational narrative well but leaves too much undocumented for an agent to invoke it reliably.

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 description coverage is 0% for all three parameters (vault, model, batch_size). The description only indirectly implies what 'model' means (the shadow model) and says nothing about vault scoping or batch_size limits, so it fails to compensate for the documentation 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?

States a specific verb and resource — backfilling embeddings for a secondary/shadow model across every chunk in the vault — and explicitly differentiates the shadow model from the active one. An agent can immediately tell this apart from sibling tools like switch_active_model or vacuum_embeddings.

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?

Gives clear sequencing guidance: run this, then run switch_active_model once complete to promote the shadow. It also clarifies the run is safe to do concurrently with search. It stops short of stating when NOT to use it or what to do on failure, so it is strong but not exhaustive.

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