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

Annotations already declare readOnly/idempotent/non-destructive, so the description correctly spends its budget elsewhere: determinism ('never invokes another AI model'), bare-place-name auto-resolution to a curated best-effort match with alternatives noted, and host-dependent interactive rendering. These are real behavioral traits not derivable from annotations, though rate limits or failure modes are unmentioned.

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 imperative purpose, then usage, then return shape, then routing exclusion, then caveats. Dense and mostly waste-free, though the return-value sentence partially duplicates what the output schema already covers.

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?

For an 11-parameter calculation tool with an output schema and full annotation coverage, the description supplies the key missing behavioral context (determinism, place resolution, host rendering). The gap is parameter semantics: an agent still cannot infer what focus, language, timezoneOffset, or birthTimeAccuracyMinutes do.

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% across 11 parameters, so the description carries the full burden and largely fails. It clarifies only the geo inputs (explicit latitude, longitude, IANA timezone) and place auto-resolution; date/time formats, name, focus, language, timezoneOffset, and birthTimeAccuracyMinutes are left entirely to bare type/pattern constraints.

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 ('SHOW THE BIRTH CHART') and enumerates the outputs (Lagna, planet table, Vimshottari, Panchanga, Navamsa), which is specific and agent-actionable. It differentiates from consult_jyotishya but says nothing about how it differs from close siblings like calculate_south_indian_chart or render_chart, which appear to produce overlapping artifacts.

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 an explicit trigger ('use when the person wants to see their chart...') and an explicit exclusion with a named alternative ('For interpretation of a question use consult_jyotishya instead'). It does not address when to prefer it over the other chart-producing siblings, so routing is clear only on one axis.

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