Skip to main content
Glama

List computations

list_computations
Read-only

The computations issues rest on, as their runners reported them: state, progress, the commit and repository, the job's page and output, and what came of it. With 'key', one issue's; with 'projectKey', the project's, newest first and the ones still going on top — state 'open' (queued or running) is what is going now, which is the first thing to ask after a lost session instead of reading status comments. 'state' may also be one of queued, running, done, failed, cancelled, lost. Each job carries what it spent — 'machine', 'cores', 'cpuSeconds', 'wallSeconds', and 'spend' worked out from them in seconds ('machineSeconds' is the measured CPU time, or cores × wall clock where none was measured, and then 'estimated' is true); with 'key', 'spend' also sums the issue's own jobs and those of the work under it (sub-tasks, an epic's stories). Each job's 'cost' says what it came to in US dollars and what that rests on — 'basis' 'reported' (the service's own bill, sent as costUsd), 'tariff' (Modal's tariff by the second) or 'share' (a share of one of our machines' monthly price by load: the core-hours it held at price ÷ (cores × hours in the month)); 'estimate' true where the machine's price is an estimate or its type was assumed; 'fx' the exchange rate a price in euros was converted at; 'usd' null with 'missing' ('price', 'gpuRate', 'rate') where it cannot be known — never a zero. 'spend.cost' sums them like 'spend'. The prices are list_machine_prices. A project's machine-hours and costs over a period are computation_hours.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_computations"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoOne issue's computations, e.g. 'MATH-74'.
limitNoHow many, for a project (default 50, max 200).
stateNoOnly this state, or 'open' for queued and running together.
projectKeyNoA project's computations, e.g. 'MATH'. Ignored when 'key' is given.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint true and destructiveHint false, so the safety profile is covered; the description's added value is the ordering rule (newest first, still-running on top) and the disclosure of how derived values behave — 'spend' aggregation across sub-tasks, 'estimated' flags, 'fx' conversions, and 'usd' being null with a 'missing' reason rather than zero. What holds it below 5 is the absence of any pagination/cursor behavior beyond the implicit limit.

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 first sentence is well front-loaded, but the body becomes a single run-on passage with dense em-dash parentheticals and a nested cost taxonomy (basis reported/tariff/share, estimate, fx, usd/missing) that reads like output documentation rather than selection guidance. Every clause is informative, but the lack of structure makes it slower to scan than its length warrants.

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?

With no output schema, the description carries the full burden of explaining return values and does so thoroughly: field-level meaning, cost derivation per job, monthly-price-by-load share math, and the null/basis semantics. Combined with the annotation safety profile, nothing essential for calling this correctly is missing.

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 100%, so the schema already documents key, limit, state and projectKey, including the 'Ignored when key is given' precedence. The description reinforces the 'open' shortcut (queued plus running) and the ordering implied by limit, but adds nothing new about limit's default/max and introduces no syntax or format detail the schema lacks — baseline 3.

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?

The opening clause states a specific verb and resource: the computations that issues rest on, as reported by runners, with the fields returned enumerated (state, progress, commit/repository, job page/output, outcome). It also disambiguates from two nearby siblings by name: machine-hours and costs over a period are computation_hours, and prices are list_machine_prices.

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?

It gives explicit routing: with 'key' one issue's jobs, with 'projectKey' the project's, and it names the alternative source of the same information (reading status comments) that should not be used after a lost session. It also directs spending/period aggregate questions to computation_hours and price lookups to list_machine_prices.

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