Skip to main content
Glama

read_series

Idempotent

Retrieves a time series for one concept and entity across a date window from cached local data or routed registry sources, including source provenance and coverage gaps.

Instructions

Read a series for one concept x entity over [start, end].

Local concepts (numeric concept_id): serves the stored cache only, highest-ranked source per point, ordered by date. It NEVER dispatches upstream — an empty window is a coverage fact reported as such, not a failure. Use read for a point read (cache + live dispatch) or fetch to force a refresh of one point.

Registry-only indicators (semantic_code / native_code as concept_id): the window is routed transparently through the indicator's source database read channel (same response shape; entity carries the region/country/city when the channel needs one). Provenance travels in each point's source_used.

scope (optional): restrict this call to a named retrieval scope — out-of-scope indicators return an explicit out-of-scope response; the reserved name unscoped forces the full corpus.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "concept_id": "<concept_id>"
    },
    "name": "read_series"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNowindow end, inclusive
scopeNooptional named retrieval scope
startNowindow start, inclusive ('YYYY-MM-DD'; a bare 'YYYY' works)
entityNoregion / country / city name for registry-only reads
entity_idNoentity id — local reads
fill_gapsNofetch the missing intervals of this window (price concepts only, additive — never overwrites a stored value)
concept_idYesconcept (local numeric id, or registry semantic_code)
entity_typeNoentity type (country, stock, fund, ...) — local reads

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing that local reads never dispatch upstream, that an empty window is a coverage fact rather than a failure, that registry reads route through the indicator's source channel, and that provenance appears in each point's source_used. The gap is fill_gaps: the description never mentions it, which is notable given readOnlyHint=false — an agent cannot tell from the prose why this 'read' tool is not read-only, and the absolute claim 'It NEVER dispatches upstream' is only true for the non-fill_gaps path.

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 core statement, then cleanly partitioned into local-concepts, registry-only, and scope paragraphs — each addressing a distinct decision. It is on the long side with some prose flourish ('reported as such, not a failure'), but no sentence is redundant.

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

Completeness4/5

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

An output schema exists and provenance is described, so return values are adequately covered for a complex dual-mode tool with 8 parameters. The remaining hole is fill_gaps (price-concept gap filling, additive and non-overwriting) and the associated explanation of why the tool is not strictly read-only.

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; the description earns more by adding semantics the schema lacks — concept_id's dual integer/semantic_code interpretation with different routing per form, entity's role as region/country/city only for registry-only reads, and scope's out-of-scope response behavior plus the reserved 'unscoped' value.

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?

Opens with a specific verb, resource, and dimensional scope: "Read a series for one concept x entity over [start, end]." It then splits the two operational modes (local numeric concept_id vs registry semantic_code) and names the siblings it is not (read for point reads, fetch for forced refresh), so an agent can place it precisely.

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

Usage Guidelines5/5

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

Explicit routing guidance: use read for a point read (cache + live dispatch) or fetch to force a refresh of one point. It also states the condition for each concept_id flavor and the condition under which scope applies, including the reserved 'unscoped' escape hatch. Nothing essential is left to inference.

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