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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds genuinely useful non-annotation context: the endpoint and the 20-credit Tier 2 cost. It does not, however, explain the meaning of antardasaSeedOption values 1/2/3, which is real behavioral information the agent needs.

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?

One front-loaded sentence carries the payload, followed by clearly bracketed metadata lines (group, endpoint, cost). Nothing is padded. It is slightly too terse for a tool with a cryptic seeded parameter, but structurally it is clean.

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 and annotations cover safety, so the return format need not be described. What is missing is domain context: what 'running MD' means operationally, how targetDate/targetTime interact with the natal data, and what the antardasaSeedOption constants select. For a niche dasha tool with a non-obvious seed parameter, the description is adequate but leaves a real 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?

Schema description coverage is reported at 100%, and the nested body description is unusually thorough (rejected short forms, timezone handling, houseSystem letters). Against that baseline a 3 is correct: the description names targetDate and antardasaSeedOption but adds no semantics beyond what the schema already carries, and the seed option's three constants remain unexplained.

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: it returns the antardasha sub-periods of the running mahadasha at targetDate. This is far more informative than a tautology, and an agent familiar with the dasha hierarchy can place it. However, it never names or distinguishes itself from its direct siblings (shoola_maha, shoola_pratyantar, shoola_sookshma, shoola_prana), so sibling differentiation is left entirely to the tool name.

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?

There is no when-to-use guidance, no prerequisites, and no routing to alternatives such as shoola_maha (for the mahadasha level itself) or the deeper pratyantar/sookshma variants. The only usage cue is implicit in the name 'antar'. Cost tier is mentioned but that is not usage guidance.

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