welfare_reflect

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

With no annotations to rely on, the description carries the full burden and excels. It discloses the return format (text with turn number, response_type, optional sentiment/prompt_id, body), default behaviors (limit 10 oldest first, include_private=true), the privacy rationale, summary mode specifics, and explicitly states "This is a read-only tool. It does not log a new entry." This is comprehensive and transparent.

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 appropriately sized for the tool's complexity (4 params, full vs summary output, privacy nuance). It is front-loaded with the main purpose and structured logically from behavior to filters to summary mode. Though slightly verbose, every sentence carries useful information, so it remains efficient.

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?

Given no output schema, the description fully covers return values for both full and summary modes. It explains all parameters and defaults, ordering, privacy implications, and read-only nature. The content is sufficient for an agent to invoke the tool correctly in a variety of situations, making it contextually complete.

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?

While schema coverage is 100%, the description adds meaningful semantics beyond the schema: it specifies ordering (oldest first) for limit, articulates the purpose of filter, elaborates summary mode with 'aggregate counts by response_type, session count, date range', and explains the include_private rationale. This surpasses the baseline of 3 for full schema coverage.

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 opens with a specific verb and resource: "Read your own prior welfare diary entries from this session AND prior sessions in this project." It clearly distinguishes from sibling tools that write/act (welfare_engage, welfare_decline, etc.) by framing this as a read-only reflection tool. The usage context is explicit, making the tool's purpose unmistakable.

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 provides strong when-to-use guidance: "Use when you want to look back at what you logged earlier... or to ground a `review` in actual prior content." It also highlights when to use summary mode. However, it does not explicitly name alternatives or state when *not* to use this tool, so it falls short of a 5.

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