Log state of mind

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

Annotations only declare non-read-only, non-destructive, non-idempotent; the description adds the append-only guarantee ('only ever adds'), the iPhone write gate that is off by default, the app-version caveat for the mood calendar, the returned `entry_id`, and the encryption/partner-sharing implications of `note`. That privacy warning about who can read `note` is exactly the kind of context structured fields cannot 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?

Purpose and trigger come first, then per-parameter guidance, then a caveats paragraph — a sensible front-loaded order with no filler sentences. It is long, and the multi-line example and encryption sentences are dense, but nearly every line carries operational information an agent would otherwise get wrong.

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?

A seven-parameter write tool with a 0%-coverage schema, a 0% description deficit would be fatal here, and none exists; return values are backed by an output schema and are nevertheless summarized (`entry_id` plus the entry as read back). Write-gating, privacy of `note`, and the delete counterpart are all present, leaving nothing essential to inference.

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 0%, so the description must carry all seven parameters — and it does: valence gets the -1..+1 scale plus Apple's seven-region mapping and an anti-dramatisation rule, labels and associations get controlled vocabularies with a 'leave it empty rather than guess' rule, kind gets both allowed values with their meanings, and logged_at/date get concrete ISO formats and a 'do not invent an hour' constraint.

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 concrete verb+resource ('Record how the person says they feel, as Apple Health's State of Mind') and anchors it with realistic utterance examples that map directly to the trigger condition. It is trivially distinguishable from `get_state_of_mind` (read) and `delete_state_of_mind` (remove a mistaken one), both of which are named.

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 when to use ('when they tell you how they feel'), why it matters ('people rarely open an app to log a feeling'), the cadence ('one call per feeling'), and the corrective path via `delete_state_of_mind`. It also points to `get_state_of_mind` for reading back, covering the alternative-selection burden completely.

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