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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, and the description adds the priced-call facts that structured fields do not carry: 20 credits, Tier 2, POST endpoint. It does not describe what the response contains beyond the concept, but an output schema exists, so the remaining gap is narrow.

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 substantive definition is front-loaded in one sentence, followed by a compact bracketed metadata block. The bracket lines are boilerplate rather than wasted prose, and there is no filler, though the astrological gloss ('karma unilluminated') occupies space that could have gone to usage guidance.

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 15-parameter chart computation, the definition establishes minimum viability: an agent knows what it computes, that four fields are required, and that the call costs credits. It omits how the heavy optional surface (house system, ayanamsa, seasonal timezone handling) affects results, which matters because different defaults change which houses are even identified as blind.

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 needs to carry weight here and does not. It restates the four required fields (date, time, latitude, longitude) that the schema already marks required, and is silent on the eleven optional ones, including consequential choices like houseSystem, ayanamsa, zodiacType, and cosmogram.

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 first sentence defines the computation precisely: 'Houses with no planet AND no Parashari aspect', which tells an agent exactly what set of houses this returns. It is a definition rather than a verb phrase, and it never distinguishes itself from the sibling astroway_vedic_lal_kitab_sleeping_house, which is a closely related Lal Kitab concept a caller could easily confuse it with.

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 description says what a blind house means astrologically and that 'remedies are essential', but never says when a caller should request this endpoint or which sibling to use instead for adjacent Lal Kitab queries (sleeping_house, remedies, lal_kitab_full). There are no exclusions or prerequisites, so usage must be inferred 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.