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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is given. The description adds context annotations cannot carry: an account/sign-in requirement, the restriction to profiles saved on the user's AstroCalc account, and the rule that bride/groom ordering follows the saved genders. The one gap is it says nothing about what happens when a name is ambiguous or not found.

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 purpose and output scope are front-loaded, and the alternative-routing sentence comes last, which is the right order. The trailing enumeration of five sibling tools is slightly longer than needed to make the point and costs a small amount of density.

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?

There is no output schema, so the description carries the burden of describing return content, and it does: Guna Milan with all eight kootas plus cancellations, and Manglik status for both people. Combined with the auth and profile-source constraints, an agent has everything needed to decide whether to call it and what to expect back.

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 coverage is 100%, so the baseline is 3. The description earns a bump because the schema gives profile_a and profile_b identical text, while the description supplies the missing semantic distinction: which argument is treated as bride versus groom depends on the saved genders, so argument order matters.

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 names the specific operation (marriage compatibility between two saved people), the scoring system (36-point Guna Milan / Ashtakoota with 8 parts and cancellations), and the second check (Manglik for both). It also distinguishes itself from the sibling kundli_milan, which takes birth details typed in chat rather than saved profiles.

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 explicit triggering phrasing ('whether two saved people are compatible', 'a match for a son or daughter', 'Manglik dosha between them') and names the alternative path (free_kundli, kundli_milan, explain_dasha, full_chart, life_timeline) for users without saved profiles. The when-to-use and when-not-to-use conditions are both covered.

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