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

Annotations are minimal (only hint flags), so the description carries the burden. It discloses important behavior: returns a warning with conflicting entry IDs on overlap, infers period_start/end and ratings from the user's language, and allows logging any subset of rating fields. This goes well beyond the annotations, though it does not describe the success response format.

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 about 150 words and organized into clear segments: usage, period types, conflict behavior, and inference rules. It is front-loaded with the core purpose and uses bullet-like lines for inference. Some redundancy (e.g., repeating defaults) is present, but overall each section earns its place.

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 7 optional parameters, a full schema, and an output schema (signal indicates it exists), the description covers the key decision points: when to log, how to handle overlaps, and how to infer unstated parameters. It does not mention authentication or rate limits, but these are not relevant for a client-side logging tool in this context. The agent has enough to call it 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 coverage is 100%, so the schema documents all 7 parameters. The description adds value by specifying inference rules for period_start/end (default today, week = Monday–Sunday, month = first–last day) and for ratings (e.g., 'exhausted'=2, 'great energy'=8). It also clarifies that any subset of rating fields may be logged. This supplements the schema meaningfully.

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 clear verb ('Log') and a specific resource ('subjective wellbeing ratings') and further clarifies the scope: day, week, month, or custom range. This distinguishes it from sibling tools like update_wellbeing (modify) and list_wellbeing (read), even without naming them.

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?

Explicitly says 'use: logging request or concrete wellbeing report to record' and excludes 'Question, general pattern or venting alone: no write.' That is clear when-not guidance. It does not explicitly name alternative tools (e.g., update_wellbeing for editing), but the positive and negative conditions are sufficient for an agent to decide.

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