Faf Gemini

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

With no annotations, the description carries the full burden and does well: it discloses non-destructiveness, faf-managed block injection, preservation of hand-written content, and idempotent re-run behavior. Auth/prerequisite context is absent, but the behavioral profile is otherwise 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?

The core action is front-loaded in the first sentence, and details follow usefully. Some phrasing is dense/redundant (the parity clause plus the convention parenthetical), but every sentence adds real information.

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 description adequately covers what is written and how it merges with existing content. Only the lone parameter's semantics are left under-specified.

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?

One parameter with 0% schema description coverage. The description implies the .faf source ('from a .faf file') but never names or explains the `path` parameter, its default, or accepted values, so compensation for the coverage gap is only partial.

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 specific verbs and resource ('Export and write GEMINI.md from a .faf file') and the generated artifact's convention (hierarchical, @file-importable). It is distinguishable from siblings, though it does not explicitly contrast itself with any of them by name.

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 by the description ('in parity with faf-cli's `faf export --gemini`') but there is no explicit when-to-use vs alternatives guidance or exclusions among the many faf_* siblings. An agent must infer that this tool targets Gemini specifically.

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