list-models

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is fully covered. The description adds that results are grouped by family and include effort levels and purpose, which is modest extra value. It says nothing about auth requirements, freshness of the model list, or whether the catalog is static or remotely fetched, despite openWorldHint implying remote data.

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 first sentence is well-formed and front-loads purpose and output shape. The second sentence is misplaced: it describes how to supply a `model` argument for some other tool, not how to call this one, and it consumes roughly half the description's length with content an agent cannot act on here.

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?

An output schema exists, so return values need not be explained and the grouping/effort detail is a bonus. But the description never tells an agent the practical purpose of the list — presumably to pick a model for the `*-antigravity` siblings — and the dangling `model` parameter reference leaves the reader unsure whether this tool consumes input at all.

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 tool takes zero parameters, which normally earns the baseline 4. However, the description instructs the reader to 'Pass a label, a full ID, or a base ID plus `effort` as the `model` parameter' — a parameter that does not exist in this schema. That is actively misleading rather than merely uninformative, so the baseline is reduced.

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 opens with a specific verb and resource — 'List the models available to Antigravity CLI (`agy models`)' — and adds that results are grouped by family with accepted `effort` levels. That is enough for an agent to distinguish it from siblings like `version` or `health`. It falls short of 5 because the second sentence drifts into describing a `model` parameter that this tool does not have, muddying what the tool itself does.

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?

There is implicit guidance: the mention of labels, full IDs, and base ID plus `effort` signals that this list is meant to feed model selection elsewhere. But there is no explicit statement of when to call this versus alternatives (e.g., before `ask-antigravity` or `delegate-antigravity`), and no exclusions. Usage is inferred rather than stated.

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