faf_etch

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

Description discloses that it's a write operation (consistent with readOnlyHint=false), returns an ID, and mentions re-etching updates in place (dedup). It also notes that the 'path' parameter sets session context. Annotations already cover non-readonly and non-destructive. Slight additional context could be added about overwriting behavior, but sufficient.

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: first states action and return, second gives usage guidance, third gives alternative. Every sentence earns its place. No wasted words.

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?

Tool has 6 parameters (1 required), full schema coverage, and output schema exists. Description covers purpose, usage, return value, dedup, and session context. Annotations provide readOnly/destructive info. Complete for agent decision-making.

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?

With 100% schema coverage, baseline is 3, but description adds significant value: for 'text' it specifies 'capture the why'; for 'id' it explains dedup and update behavior; for 'priority' it explains recall ordering; for 'tags' it provides usage examples and filtering coupling; for 'path' it explains session context. All add meaning beyond schema.

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 clearly states the tool's action: 'Remember a decision, gotcha, or win across sessions by writing it to the project soul (.fafm).' It also specifies the return value: 'Returns the stored memory's id.' This distinguishes it from sibling faf_recall, which reads memories.

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?

The description explicitly states when to use this tool: 'Use this to persist something an AI should recall later;' and when not to: 'use faf_recall to read them back.' This provides clear guidance and alternative.

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