Skip to main content
Glama

Create an index

create_index

Index a value in a list's items, to find items by it (alias), order, filter or search by it, or hide it from tokens (guard). The index is built in the background: until its buildStatus is ready, anything that uses it fails with INDEX_BUILDING. With wait: true this polls until it's built, at 1 metered request per poll (the result says how many). 1 request, plus the polls.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
listYesThe list: its id or pathName
nameNoThe index's name
tagsNoTags (at most 20). Replaces the existing tags
waitNoWait (up to 30 seconds) for the build to finish, polling with metered requests
aliasNoItems can be found by this value instead of their id. Values must be unique and at most 1024 characters; one alias index per list
guardNoHide the value at pointer from token reads (only an identity that owns an item can read it). Not combinable with the other flags
pointerYesA JSON pointer to the indexed value in each item's data, e.g. /score
sortingNoItems can be ordered by it
pathNameYesThe name used to filter and order by it, e.g. "score". Unique in the list, and stored lowercase
activatedNo
filteringNoItems can be filtered by it
searchingNosearch_items searches its values
valueTypeNoHow values are compared (default string)
descriptionNo
defaultOrderDirectionNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
indexYes
buildStatusYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description discloses meaningful behavior: the index builds asynchronously, consumers fail with INDEX_BUILDING until buildStatus is ready, and wait: true polls at 1 metered request per poll with an explicit cost statement ("1 request, plus the polls"). It does not cover what happens on name/pathName conflicts or permission requirements, so it stops short of a 5.

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?

Three sentences, front-loaded with the core action and then the async/cost caveats; little waste. There is mild redundancy with the per-flag schema descriptions, keeping it from a 5.

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 so return values need not be explained, and the description covers the critical non-obvious behaviors (async build, INDEX_BUILDING failure, metered polling cost). The main remaining gap is conflict/error behavior for a non-idempotent creation tool.

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 80%, so the schema already documents nearly all 15 parameters, including the alias, guard, sorting, and filtering flags. The description paraphrases those same flags (alias/order/filter/search/guard) without adding syntax or constraints beyond the schema, so baseline 3 is appropriate.

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 and resource ("Index a value in a list's items") and enumerates the purposes the index enables (alias, order, filter, search, guard). It does not explicitly differentiate itself from close siblings like update_index, rebuild_index, or list_indexes, so an agent must infer it is the creation path.

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?

Usage is implied through the enumerated index capabilities and the wait polling condition, giving an agent a reasonable sense of intent. However, there is no explicit routing guidance for when to use this versus rebuild_index, update_index, or wait_for_index, which are the natural alternatives.

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