Faf Agents

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

With no annotations provided, the description carries the full burden and does well: it declares non-destructive behavior, block-scoped injection that preserves hand-written content, idempotent re-runs, and the exact output sections authored. It stops short of stating auth/permission needs or failure modes if the file is missing or malformed.

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?

Front-loaded with the export/authoring summary and the parenthetical section list is compact and informative. Mild redundancy: 'non-destructive' is asserted twice ('non-destructive' and 'it never overwrites your file'), slightly padding the ending.

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 described, and the behavioral contract (block injection, preservation, in-place update) is well covered for a file-mutating tool with zero annotations. The only real gap is the undocumented `path` parameter and default.

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 the single `path` parameter, so the description must compensate; it only alludes to 'a .faf file' and never names the parameter, its default (`project.faf`), or accepted path formats. Partial coverage of a one-param tool, hence a middling score.

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 artifact (export/write AGENTS.md from a .faf file) and the mechanism (faf-python-sdk authoring, parity with `faf export --agents`), which clearly separates it from siblings like faf_stringify, faf_migrate, or faf_init.

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: it's the tool that produces/refreshes the AGENTS.md block, and re-running updates in place. But it never says when to prefer this over sibling tools (e.g. faf_init or faf_auto for the same file), nor any prerequisite such as a valid .faf existing.

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