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

With no annotations provided, the description carries the full disclosure burden. It does add real behavioral context: the tool computes a proportion against the whole corpus baseline, returns an interval, and ignores houses. But key behaviors remain undisclosed — what the 'interval' statistically is (confidence interval?), how empty occupation groups are handled, and whether occupation vs occupation_qid are treated as alternatives or filters.

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?

A single dense sentence that front-loads an illustrative example query, then gives the precise computation, the interval, and the signs-only scope. Every clause earns its place; there is no filler or repetition of schema content.

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 covers return values, and the core computation plus the signs-only limitation are described, which is adequate for the simple required-parameter pair (graha, znak). Yet for a 5-parameter statistical tool, the description leaves gaps: the meaning of the interval, the interaction between occupation and occupation_qid, and when this tool should be chosen over sibling corpus/comparison tools are all unresolved.

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 40%, below the 50% threshold, so the description must compensate. It partially does: it explains that znak 0 is Aries (matching the schema min/max but adding semantic meaning) and clarifies that occupation is a word and that the query binds a graha to a sign. However, it does not clarify the relationship or precedence between occupation and occupation_qid, nor add anything about lang or the graha enum values.

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 states a specific computation: share of a graha in a sign (znak 0–11, 0=Aries) within an occupation group compared against the share in the whole corpus of known people, with an interval. This is a precise verb+resource statement that goes beyond a vague label. However, it does not explicitly differentiate itself from plausible siblings like corpus_search or compare_methods, so an agent may still need to open other schemas to disambiguate.

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?

Usage context is implied through the concrete example query (

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