chat_harvest

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

With no annotations, the description carries the transparency burden. It discloses key behaviors: facts are 'queued for human review' (not immediately stored), secrets are 'redacted server-side before any LLM sees the text,' and it works across multiple IDEs/agents. It stops short of describing response formats or potential errors, but covers the most critical traits.

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 description is front-loaded with the core action, followed by context, timing, security, and alternatives. It is slightly redundant (e.g., 'tool-agnostic' and 'Works from ANY IDE/agent' both make the same point) and contains jargon ('dim harvest') that may be unfamiliar, but it remains efficient and avoids fluff.

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 simple tool with no output schema and only three parameters, the description covers the essential context: what it does, when to use it, how it handles sensitive data, and how it differs from alternatives. It does not describe the exact response shape, but the lack of output schema makes that less critical.

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 baseline is 3. The description reinforces the main parameter ('pass the messages the USER typed this session (verbatim)'), but this largely repeats the schema's existing parameter descriptions. It does not meaningfully add semantics beyond what the schema already provides.

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 function: harvest the current chat session by passing user messages verbatim to extract durable facts for human review. It explicitly differentiates itself from siblings by positioning as 'the live, tool-agnostic equivalent of dim harvest' and by recommending context_note for single facts.

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 explicit guidance on when to use: 'Call at session end, or after a long exchange rich in project knowledge.' It also names an alternative for a specific use case: 'For single facts stated in passing, prefer context_note instead.' This gives the agent clear decision criteria.

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