Naksha Muhurat

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 fully covered. The description adds useful scope boundaries but says nothing about what a result looks like (a verdict? a window? reasons?) or how the purpose enum affects the answer, which matters since there is no output schema.

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?

Two sentences, zero filler, and the affirmative trigger is front-loaded before the exclusions. Every clause carries routing information.

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 a read-only, idempotent screening tool with fully documented parameters and annotations covering safety, the definition is nearly sufficient. The remaining gap is that with no output schema, the description never hints at the shape of the answer (pass/fail, reasons, timing windows).

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% with an enum on purpose and patterns/lengths on date and city, so the schema does the heavy lifting and 3 is the baseline. The description's prose purpose list (marriage, vehicle purchase, property registration) roughly maps to enum values (vivah, vehicle, property) but adds no syntax or constraint detail beyond the schema.

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 specific verb+resource ('check whether a specific date works') and enumerates the five screened purposes, which maps cleanly to the purpose enum. It is clear on its own, but it never names or contrasts with the sibling find_muhurat, leaving the agent to infer the split between 'screen this date' and 'find dates'.

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 ('when the user asks whether a specific date works...') and a solid when-not list excluding horoscope matching, guaranteed outcomes, remedies, and family tradition decisions. It stops short of pointing to the alternative tool (find_muhurat) for the cases it declines, so routing is only half-solved.

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

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds a meaningful boundary ('not for guaranteed outcomes'), but says nothing about how dates are screened or what the result looks like, and no output schema exists to fill that gap.

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 'Use this when', followed by trigger examples and then exclusions in one sentence each. The example list is somewhat long but every phrase maps to a real query pattern, so little is 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?

For a four-required-parameter tool with no output schema, the description never explains what comes back (a list of dates? ratings? windows per day?) or whether results are paginated or bounded by the requested month. The usage triggers are complete, but the return contract is absent.

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 baseline is 3, but the description goes beyond the schema by decoding the enum values ('vivah' = marriage, 'griha_pravesh' = housewarming, plus vehicle, property, mundan) into real user situations. It does not clarify city's role or the month/year format, which the schema already handles.

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 examples ('griha pravesh muhurat october 2026', 'vehicle purchase muhurat') plus the phrase 'screened dates' make clear this returns auspicious dates for a given purpose, month, year and city. It is not a pure verb+resource statement, but the intent is unambiguous and distinguishable from check_date.

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?

Explicit trigger phrases are given, and exclusions are spelled out: guaranteed outcomes, horoscope matching, remedies, replacing a family astrologer. It does not, however, contrast with the sibling tool check_date, leaving the boundary between 'find a range of dates' and 'check one date' implicit.

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