faf_claude

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the mutation is expected and the safety profile is partially covered. The description adds real value beyond that: it discloses the faf-managed block boundary and that surrounding content is preserved during the write, and it states the return payload ('the files written'). It does not describe overwrite behavior when no managed block exists.

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-loads the primary output and direction before the optional-format detail, and the parenthetical legacy-name note is compact. The middle clause about preserved content is load-bearing rather than filler, though the sentence runs long with several parentheticals.

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 write tool with no output schema, the description covers what is written, where the write is bounded, that files are reported back, and how to expand the output set. The main remaining gap is precedence among the flags and 'all', which the schema hints at but never resolves.

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%, so every parameter including 'all' and the per-format booleans is already self-documenting; baseline is 3. The description references the format flags and 'all' but adds no syntax, interaction rules, or precedence detail beyond what the schema already conveys.

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 ('Write CLAUDE.md from project.faf') and pins the direction of the operation with '.faf → CLAUDE.md', which is genuinely distinguishing detail. It also enumerates the additional artifacts the format flags produce. It stops short of differentiating itself from the near-identically named siblings faf_agents, faf_cursor, and faf_gemini, which an agent would reasonably confuse with the flag-driven behavior here.

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?

Provides a clear motivating context ('Use this to keep every AI tool's context file current from one source') and implies the flag-based fan-out path, plus a rename note for older callers. It never states when NOT to use this tool or when to prefer the individual faf_agents/faf_cursor/faf_gemini siblings over the flags.

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