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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds real behavioral context beyond that: aspects are returned most-exact-first, ascendant/midheaven appear only when birth time is known, and a link to the site's double chart is included. It does not describe response size or limits, which keeps it short of a 5.

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?

Three sentences, front-loaded with what is computed, then the input shape, then the scope limit. Almost every clause carries information; the closing note about the link is mildly promotional but still tells the agent something about the response.

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?

With an output schema present, the description need not explain return values, and it covers the nested person-object contract and the ordering guarantee. The one substantive omission is the semantics of house_system, which an agent cannot resolve from any supplied field for a tool involving two charts with possibly different house systems.

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?

Coverage is only 33% at the top level, but the description compensates by spelling out each person object: date, optional time, and place or lat/lon/tz, plus optional name. The notable gap is house_system, an enum parameter documented nowhere in either the schema or the description, so the agent has no basis for choosing placidus vs whole.

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 ('Compares two birth charts') and then enumerates exactly what is computed: inter-chart aspects with exactness ordering, and each person's planets in the other's houses. That level of specificity makes it clearly distinguishable from siblings like birth_chart (single chart) or transits without opening any schema.

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?

It scopes the tool explicitly with 'Calculations only, no reading of the relationship', which tells the agent not to expect interpretation. However, it never names the alternatives (birth_chart for one person, transits for time-based comparison), so an agent must infer the sibling routing on its own.

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