Skip to main content
Glama

The three things to hear first, with what backs them

get_reading_plan
Read-onlyIdempotent

Picks the three findings a person should hear first from hundreds of candidates (fired book rule cards, rare chart facts measured against 5,000 ordinary charts, period and transit changes in the next 18 months, agreement across Parashari, Jaimini and KP) and returns a reading plan: headline insights, supporting claims, timing windows, cautions, 1-3 past windows to confirm, and sources. Each claim carries its facts, citations, base rate, confidence and school. Nothing common to most charts headlines, nothing that flips if the birth time is off by 15 minutes, and nothing about death, longevity, illness, fertility or separation. Narrate the plan; do not add claims to it.

Input Schema

NameRequiredDescriptionDefault
asOfNoReading date (YYYY-MM-DD); default today.
dateYes
nameNo
timeYes
placeNo
topicNo
latitudeNo
questionNo
timezoneNo
longitudeNo
seenClaimIdsNoClaim ids already told to this person; they rank lower.
timezoneOffsetNo
birthTimeAccuracyMinutesNo

Output Schema

NameRequiredDescriptionDefault
timingYes
sourcesYes
cautionsYes
headlineYes
pastChecksYes
supportingYes
schemaVersionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description goes well beyond that by disclosing the candidate pool, the per-claim metadata (facts, citations, base rate, confidence, school), and hard editorial filters — nothing common to most charts, nothing that flips with a 15-minute birth-time error, nothing on death/longevity/illness/fertility/separation. Those filtering rules are behavior an agent could not infer from structured fields.

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

Conciseness3/5

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

The purpose is front-loaded in the opening clause, which is good. But the middle sentence is a very long run-on carrying a dense parenthetical catalog of candidate sources (book rule cards, 5,000-chart base rates, transits, school agreement) that reads more like internal pipeline detail than selection-relevant information, and the final sentence mixes two unrelated constraints.

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 the description needn't explain return values, and it nonetheless does — helpfully. What is missing is coverage of a 13-parameter input surface at 15% schema documentation; an agent must guess at topic, question, location-vs-coordinates, and birth-time accuracy semantics from names alone.

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

Parameters2/5

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

Schema description coverage is only 15%: just asOf and seenClaimIds are documented, leaving 11 parameters (place, latitude/longitude/timezone, topic, question, birthTimeAccuracyMinutes, etc.) with no schema text. The description barely compensates — the '15 minutes' remark hints at birthTimeAccuracyMinutes and the seenClaimIds ranking effect is restated only in the schema, while the location/date/topic inputs and the anyOf place-vs-coordinates branch go unexplained.

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

Purpose5/5

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

States a specific verb and resource ('Picks the three findings a person should hear first') and immediately enumerates the return payload: headline insights, supporting claims, timing windows, cautions, past confirmation windows, and sources. That level of specificity clearly separates it from narrower siblings like analyze_chart_topic or get_compact_chart_evidence, which surface evidence rather than a ranked three-item plan.

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

Usage Guidelines3/5

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

The closing line 'Narrate the plan; do not add claims to it' is a real usage instruction about what to do with the output, and the exclusion rules imply this is a final synthesis step rather than an evidence-gathering step. However, there is no explicit when-to-use/when-not guidance and no named alternative for agents that want raw evidence instead of a curated plan.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources