llm_autodetect

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

With no annotations provided, the description carries the full behavioral burden. It does disclose the key mutation trait — that discovered engines are 'automatically sync[ed] into your Antigravity vault' — and the network-probing behavior. However, it does not disclose side effects like whether existing vault entries are overwritten, whether probing can be disruptive, or any failure behavior when no servers respond. Adequate but not rich.

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?

A single dense sentence is front-loaded with the verb and target ('Auto-scan local network ports for running AI servers'), and the port enumeration is genuinely useful operational detail rather than padding. It is slightly dense — seven server/port mappings plus a three-part outcome clause — but nothing is wasted.

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 zero-required-parameter detection tool, the description covers the core behavior well: what is scanned, what is discovered, and what happens to the vault. Since there is no output schema, the description could more explicitly specify the return shape (though 'lists their active models' hints at it). Minor gaps — no mention of the no-results case or how vault conflicts are resolved — keep it just short of 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 description coverage is 100% — all three optional parameters (auto_sync with its default and effect, timeout_ms with its default, custom_ports with an inline example) already carry full semantics in the schema. The description adds no parameter-level detail beyond the schema, so the baseline of 3 applies.

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 names a specific action ('Auto-scan local network ports' / 'Detects online engines') with a concrete resource ('running AI servers', 'Antigravity vault') and enumerates the exact servers and ports probed (Ollama, LM Studio, vLLM, etc.). This clearly distinguishes it from siblings like llm_test_connection, llm_list_models, and llm_manage_providers — an agent can tell this is the discovery/sync tool without opening a schema.

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?

Usage is implied but never stated explicitly. The description conveys this is for detecting and syncing local AI servers, but it does not name alternatives (e.g., llm_test_connection for testing a single known endpoint, llm_manage_providers for manual vault edits) nor provide when-not-to-use guidance. The sibling names hint at the boundaries, but the description itself leaves the routing to inference.

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