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

Annotations only cover read-only/idempotent/non-destructive, and the description adds genuinely non-obvious behavior: account-free operation, nothing persisted, the returned chartContext is sensitive and expires after two hours, and ambiguous birth details can yield clarification data instead of a chart. These are consequential runtime traits an agent could not infer from the structured fields.

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 is front-loaded in the first sentence and every subsequent sentence carries distinct information. The middle sentences are heavily comma-and-semicolon-joined, compressing defaults, precision modes, place semantics and return behavior into run-ons that cost readability, plus the return-value sentence partly duplicates the output schema.

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 a nested two-parameter schema with 0% description coverage plus an output schema and full annotations, the description covers the important surfaces: required field, defaults, time-precision variety, place vs. viewing timezone, non-persistence, and expiry. The main omission is any explanation of ambiguity resolution (disambiguation enum) despite advertising clarification data as a possible outcome.

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?

With 0% schema description coverage, the description does real work: it names the time precision modes (exact, approximate with minutes, bounded_range, day_period), states that omitted time and timeSource default to unknown/unspecified, and distinguishes 'birthplace is a historical city' from 'calendarTimezone is a separate viewing timezone'. It leaves gaps, though: the disambiguation parameter (reject/earlier/later), place.countryCode and place.sourceRecordId, the separate birth 'timezone' field's relation to calendarTimezone, and the 720-minute cap on uncertaintyMinutes are all unaddressed.

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 — 'Calculates an account-free temporary natal chart from supplied birth details' — with the scope-defining qualifiers 'account-free' and 'temporary'. The closing 'No profile, chart or analysis is saved' implicitly separates it from saved-chart siblings like get_chart, but that contrast is never made explicit by naming the sibling.

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 establishes prerequisites (birth date required, defaults for time/source) and implies the temporary/unsaved nature of the result, which nudges an agent toward the saved-chart siblings for follow-up. However, it never states when to choose this over get_chart or get_profile, and offers no explicit exclusions.

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