Tri-Sync to MEMORY.md

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

With annotations covering safety (idempotent, non-destructive), the description adds real behavioral value: it localizes the target path, CLAUDE_CONFIG_DIR override, and — crucially — specifies that only the managed block changes, all of Claude's notes are preserved, and the reply is asserted only after reading the file back. That verification and preservation guarantee goes well beyond what readOnlyHint/destructiveHint convey.

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?

Three sentences, no filler, front-loaded with the primary action and target before the readback guarantee and sibling routing. Every sentence earns its place, including the path and config-dir override.

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?

No output schema exists, yet the description tells the agent what the reply means ('the reply says so only after reading the file back') and what is and isn't modified. For a 2-param write tool with no return schema, this is complete enough to invoke correctly.

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 both parameters are already documented. The description repeats the 'status reads only' and default-export semantics that the schema's enum description already carries, adding no syntax or edge-case detail. Baseline 3 is correct.

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?

Names a specific verb and resource ('Write project.faf as a faf-managed block into the MEMORY.md'), states the exact target file and its location, and explicitly distinguishes itself from the sibling faf_sync ('faf_sync writes CLAUDE.md'). An agent can pick between the two without opening either 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?

It routes the agent to an alternative (faf_sync for CLAUDE.md) and disambiguates the 'status' mode as reads-only. It does not spell out prerequisites or when-not-to-use beyond the sibling contrast, so it stops short of the top band.

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