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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the scoring model (sunrise-panchang with tithi/vara/nakshatra/yoga/karana), the presence of goodDates/bestDate, and an explicit limitation ('No lagna windows: the scanners compute none'). That limitation plus the credit cost is exactly the kind of trait annotations cannot express; the only missing behavior is how the 0/0 lat-long default affects scoring.

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 dense but well front-loaded sentence leads with the core operation before enumerating factors and output fields. The field enumeration (score, rating, suitable, barredBy, goodDates, bestDate) is partially redundant given an output schema exists, but it still reads as purposeful rather than padded.

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?

Group, endpoint, required params, and cost are all present, the output schema covers return shape, and the scoring method plus the lagna limitation give the agent enough to trust the results. The remaining gap is that coordinate/timezone inputs are not flagged as consequential for a day-by-day judgment spanning a whole month.

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 67%, so the schema already documents month format, the activity enum, ayanamsa, timezoneOffset, and compact-mode fields. The description's restatement of the month format and activity-keys source adds nothing new, and it stays silent on latitude/longitude, whose silent 0/0 default materially changes results for a muhurat calculation. Baseline 3 is appropriate.

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 precise verb and scope: every day of an (YYYY-MM) month judged for one activity. It anchors itself against siblings by naming the per-activity scorer (/vedic/muhurat/<activity>) and the type-lookup tool (GET /muhurta/types), so an agent can place it in the muhurat family without opening a schema.

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?

The 'month view' framing plus the note that `activity` values come from the types endpoint implies when this is used, and it cites a cost (50 credits, Tier 3) that helps triage. However, it never explicitly says when to prefer this over the single-day activity tools or the report tool (astroway_reports_muhurta), nor does it state prerequisites such as needing coordinates for a meaningful result.

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