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

Annotations already establish the safe, idempotent, closed-world read profile, so the description's job is to add domain behavior — which it does by disclosing exactly what the response contains (12 named sub-types and a `partial: true` condition at 6-of-7 grahas) and by flagging the 20-credit Tier 2 cost. It stops there: no note on whether other doshas are also checked, no computation caveats, no auth context.

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 the definition, then the output contract, then cost metadata — no filler text. The inline 12-name-to-house mapping is long but each entry carries information, so it earns its space even if a list format would read faster.

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 the description's return-value explanation is therefore a bonus rather than a necessity, and annotations carry the safety profile. The weak side is the input contract: a 15-parameter chart calculation with 33% schema coverage leaves the agent without any description-side guidance on required birth data or correct Vedic settings, which is a real completeness gap for a tool of this complexity.

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, and the description says nothing about inputs at all — not the four required birth-data fields, not ayanamsa/houseSystem expectations for a Vedic dosha calculation, and not how `fields`/`precision` compact-mode interact with the subtype output. It does not compensate for the coverage gap, so the baseline for a sparse schema is not met.

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 precise computational definition ('all 7 classical grahas on one side of the Rahu-Ketu axis') and enumerates the exact output taxonomy (12 sub-types keyed to Rahu's house, plus the partial flag). That is far more specific than the bare title. It does not, however, distinguish this Parashara variant from close siblings such as astroway_vedic_doshas_kp_kalasarpa or astroway_vedic_doshas_lal_kitab_kalsarpa, which compute the same dosha under different systems.

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 or when-not-to-use guidance, no mention that this is the Parashara-school version of a dosha also offered in KP and Lal Kitab flavors, and no indication of prerequisites (it silently requires birth date/time/coordinates). The reader must infer usage entirely from the tool name.

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