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

Goes well beyond the annotations: it discloses that UTC and abbreviations are refused (so the call can fail on bad input), that country-only input requires asking for a city first, what the result contains, and the calendar side effect — calendar_out_of_date means the calendar is stale and the agent must tell the user, 'Never change the calendar yourself'. It also warns that a later calendar-zone change or web-app visit can overwrite the saved value, which is real mutation context that destructiveHint=false does not 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?

Front-loaded with the trigger conditions in the first sentence, then parameter constraints, then result shape — a sensible order. It is long (three paragraphs) and some clauses about the calendar are dense, but each carries operational information rather than padding.

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?

Covers the write semantics, refusal behavior, result fields, and the calendar-out-of-date follow-up, which is everything an agent needs to act on the response. The remaining gap is routing: with both well_set_timezone and well_update_timezone present, the description never explains which one applies.

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 baseline is 3; the description earns above that by adding the procedural rule that a country name or abbreviation should trigger a question about which city the user is in, and by stating the effect of the value ('Well reads the user's times in this zone'). workspace_id, conversation_id, idempotency_key, and workspace_scope are left entirely to the 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?

States a specific verb and resource ('Save the time zone the caller is in now') and scopes it to the caller's own zone, never another member's. What it does not do is distinguish itself from the sibling well_set_timezone, which by name appears to do the same thing — an agent has no textual basis for choosing between 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?

Gives concrete, quotable triggers: when the person states where they are, mentions travel, makes a passing correction ('I'm in Lisbon this week'), or agrees to an offered update; plus the sequencing constraint 'Call it before you answer' and 'never reply only with clock arithmetic'. No alternatives or when-not-to-call guidance are given, and the well_set_timezone alternative is never named.

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