Sahadeva

Audit reading prose against calculated placements and safety rules

audit_reading_evidence

Read-onlyIdempotent

AUDIT A READING. Checks prose against the calculated placements and safety rules and lists contradictions.

Input Schema

Name	Required	Description
`date`	Yes	Birth date YYYY-MM-DD (1800–2050)
`name`	No	Person's name or a label
`text`	Yes
`time`	Yes	Local birth time HH:MM (24-hour); 6:30 PM is also accepted
`place`	No	Catalogue query or display label when explicit coordinates are supplied
`latitude`	No
`timezone`	No	Required IANA timezone when explicit coordinates are supplied, for example Asia/Kolkata
`longitude`	No
`timezoneOffset`	No	Optional fallback offset; derived from timezone and the requested local date when omitted

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 18, 2026
- addedInput schema / properties / date / description
```
Added value: +"Birth date YYYY-MM-DD (1800–2050)"
```
- addedInput schema / properties / date / pattern
```
Added value: +"^\\d{4}-\\d{2}-\\d{2}$"
```
- addedInput schema / properties / name / description
```
Added value: +"Person's name or a label"
```
- addedInput schema / properties / time / description
```
Added value: +"Local birth time HH:MM (24-hour); 6:30 PM is also accepted"
```

Changed1 schema field changedOct 15, 2026

changedInput schema / required

Previous value: -[
-  "name",
-  "date",
-  "time",
-  "text"
-]New value: +[
+  "date",
+  "time",
+  "text"
+]

First observedOct 1, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds that the tool 'lists contradictions,' hinting at output behavior, but says nothing about what a contradiction is, how placements are sourced, or any limits beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the action front-loaded and no filler. Efficient, though arguably over-sparse for a 9-parameter tool with a domain-specific 'safety rules' concept.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return format needn't be described. However, for a tool demanding full birth data plus up to 30k characters of prose, the description omits key context: what safety rules are, how placements are computed, and what 'audit' produces conceptually.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67% (latitude/longitude/text lack descriptions), which is below the 80% threshold, so the description should compensate but does not. It never explains that the 9 inputs form a birth-data block (date/time/place or coordinates) whose chart the prose is audited against, leaving the coordinate-vs-place choice to the schema's anyOf.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('checks/audits') against a defined resource ('prose'/'reading') and names the two comparison bases: calculated placements and safety rules. This distinguishes it reasonably from siblings like audit_chart_calculation or audit_prediction_claim, though it doesn't explicitly name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides no when-to-use context, no prerequisites, and no routing to related tools such as audit_prediction_claim, get_validation_report, or validate_rule_spec. The agent must infer when auditing prose is the right call versus any of the ~80 siblings.

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

All Sahadeva tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.