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

Annotations already declare a safe read-only, idempotent operation, but the description goes far beyond them: it discloses the exact simplified retrograde/speed formula, the exception handling for Sun and Moon, the fact that the full BPHS Cheshta-Kendra method is not implemented, and a quantified divergence bound versus jhora. These are the limitations an agent genuinely needs to judge output trustworthiness.

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?

Dense but front-loaded: the tool identity leads, then the model, then caveats, then the metadata block. The formulas are technical but arguably earn their place by letting an agent reason about the strength values; there is little outright filler.

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 so return values need no explanation, and the description thoroughly covers the computational model and its limitations. However, for a 15-parameter tool with low schema coverage it omits any parameter-level guidance and any usage routing against shadbala_full, so it is adequate for behavior but incomplete for invocation.

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 only 33% across 15 parameters, so the description is expected to compensate, yet it says nothing about date, time, latitude, longitude, ayanamsa, timezone, precision, or the compact 'fields' mode. Only the implicit 'speed/retrograde' concept relates to the computation, leaving most parameters undocumented in both places.

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: 'Cheshta Bala, motional strength', which is one of the six Shadbala components and identifies it apart from siblings like shadbala_dig, kala, sthana, naisargika and drik. An agent can tell it computes one specific strength component, but the description never explicitly contrasts it with astroway_vedic_shadbala_full, which is the obvious alternative for a complete six-fold score.

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 at all: no statement of when Cheshta alone is preferable to shadbala_full, and no prerequisites such as needing a chart or ayanamsa context. The Sun=0 / Moon=0 notes explain internal scoring conventions rather than routing the agent to the right tool, so this is effectively absent guidance.

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