Skip to main content
Glama

Ranked list by signal (sale propensity, maintenance, CVA, idle...)

jt_signal_ranking
Read-onlyIdempotent

Ranked LIST of Brazilian aircraft by one precomputed signal, for prospecting ("which jet owners in SP are most likely to sell?", "which aircraft enter a maintenance window this quarter?"). Signals: sale_propensity (idle time, CVA status, recent owner change, active or stale listing, financeira owner, age and the internal model when fresh (same weights as jt_sale_propensity)); maintenance (CVA expired or expiring, heavy tracked use, drop in tracked hours, long idle time); fractional_fit (owner profile (natural person or holding), single-aircraft owner, age, tracked use, owner state, category (same weights as jt_fractional_fit)); cva_expiring (CVA expires in the next 90 days; closer date = higher score); idle (no tracked flight for 60+ days (only aircraft with tracking coverage)); owner_change_recent (owner changed in the registry in the last 12 months; more recent = higher score). Filters: owner state (uf), model or family, category, segment, minimum score, windowDays (cva_expiring and maintenance: CVA date up to today + N days; other signals: aircraft that entered the signal in the last N days), inferred base airport (base, ICAO). Each row: registration, model, year, owner (company name and CNPJ root, or "pessoa_fisica" without a name), owner state and city (labelled as the owner record), inferred base, score 0-100, the 3 heaviest factors in plain text, the date of the fact and the last registry change. The top says total before the limit and computedAt (scores are recomputed daily; the same score appears in jt_sale_propensity, jt_fractional_fit and on the web). Default 25, max 100; paginate with nextCursor. Starter shows the first 5 rows and the total. A score ranks who to contact first, never a prediction of sale.

Input Schema

NameRequiredDescriptionDefault
ufNoOwner state (UF), e.g. SP. Not where the aircraft is based.
baseNoInferred home airport (ICAO) from tracking, e.g. SBMT.
langNoLanguage of the factor texts. Default en.
limitNoDefault 25.
modelNoCatalog slug, family or name ("phenom 300", "king air"): the whole family.
cursorNonextCursor from a previous page.
signalYesWhich signal to rank by.
segmentNoOmit to let the filter decide (see segmentApplied).
categoryNojet, turboprop, helicopter, piston or a fine category.
minScoreNoOnly rows with score >= this.
windowDaysNocva_expiring/maintenance: CVA date up to today + N days (90 = this quarter). Others: entered the signal in the last N days.

Output Schema

NameRequiredDescriptionDefault
codeNoMachine-readable error code (INTERNAL, TIMEOUT, INVALID_ARGUMENT, NOT_FOUND, TOOL_FAILED, ACCOUNT_KEY_REQUIRED).
_metaNo
errorNo
foundNo
gatedNo
requestIdNo
retryableNo
quota_exceededNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

With readOnly/idempotent/non-destructive already declared in annotations, the description still adds substantial behavior: scores recomputed daily, a 0-100 scale, default 25 / max 100, cursor pagination, a 5-row starter view showing the total, and what each row contains. It also sets a critical interpretive guardrail: "A score ranks who to contact first, never a prediction of sale."

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?

Front-loaded with the ranked-list purpose and the example questions before diving into signal definitions, and every sentence carries operational content. It is dense and parenthetical-heavy, so the six-signal enumeration is slower to scan than it needs to be, but the length is largely justified by 11 parameters and 6 signals.

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

Completeness5/5

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

For a filtered, paginated ranking tool this covers what an agent needs to call it correctly: signal semantics, filter interactions, row fields, default and max limits, pagination, and the fresh-daily recompute. An output schema exists, yet the prose still surfaces the score-scale and interpretation caveats the schema cannot express.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description earns more by defining what each signal actually is (sale_propensity factors, cva_expiring = next 90 days with closer date ranking higher, idle = 60+ days with tracking coverage only) and by clarifying that windowDays means different things for CVA-based versus other signals. Remaining schema-only details (lang, cursor) are minor and adequately labeled.

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?

"Ranked LIST of Brazilian aircraft by one precomputed signal, for prospecting" gives a specific verb (rank), resource (Brazilian aircraft), and scope (single signal), backed by two concrete example questions. It also names the sibling scorers (jt_sale_propensity, jt_fractional_fit) and states that the underlying scores are identical, so an agent can tell this list view apart from the single-signal tools.

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

Usage Guidelines4/5

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

The prospecting examples ("which jet owners in SP are most likely to sell?", "which aircraft enter a maintenance window this quarter?") make the intended use concrete, and the per-signal glosses tell the agent which signal answers which question. It stops short of an explicit routing rule (e.g. "use jt_sale_propensity for a single aircraft, this for a ranked shortlist"), leaving the boundary with siblings like jt_maintenance_signal and jt_fractional_fit only implied.

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