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

The description goes beyond the annotations by disclosing what the result contains (Moon, Lagna, chart positions, dosha flags) and by imposing a non-deterministic-advice framing rule that annotations cannot express. Annotations already cover safety and openness (readOnlyHint=false, openWorldHint=true), so no contradiction and no major undisclosed behavior remains.

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 core purpose is front-loaded in the first clause, and every following sentence is a constraint rather than filler. It is slightly verbose in that the 'never guess coordinates' / 'ask the user to clarify' rules are repeated from the schema, but no sentence is genuinely wasted.

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?

An output schema exists, so return values need no prose. However, for a nested two-person schema where place, latitude, longitude, and timezone are all optional, the description never states that a location (place or coordinate pair) is effectively required — an agent could call with only date and time and silently produce degraded output. The undocumented `language` parameter is a further gap.

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?

The description's parameter guidance ('Use city, region and country', 'only verified latitude and longitude', 'never guess coordinates') largely restates what the schema properties already say in detail. It adds nothing about the otherwise completely undocumented `language` parameter, and nothing about the relationship between place and coordinates when both are absent.

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 gives a specific verb and resource ('Calculate traditional 36-point Ashtakoot ... compatibility') plus the aliases (Guna Milan, Kundli matching) and the output scope (Moon, Lagna, chart positions, dosha flags). It is clearly a two-person synastry tool, distinct from siblings like compute_chart or analyze_doshas which operate on a single chart.

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 gives concrete operational instructions: use city/region/country for a place, ask the user to clarify an unresolved place rather than retrying another tool with the same input, and never guess coordinates. It also sets a framing constraint ('Do not frame the score as a command to start or end a relationship'). What it lacks is explicit routing versus siblings such as compute_chart, so it is clear context without named alternatives.

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