Skip to main content
Glama
OperatorNest

mcp-tools

by OperatorNest
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

OperatorNest tools

Hosted MCP endpoint: https://operatornest.com/mcp (Streamable HTTP, no API key).

Five deterministic cost, time-zone and scheduling calculations use bundled data and the same tool definitions over HTTP and stdio, returning normalized inputs, units, method, assumptions, dated sources and a link to open each result on OperatorNest. No network calls. The TypeScript source is included; calculations do not create events, install schedules or execute tasks.

Tool

Result

ai_api_cost

USD per request, day and month from token counts and selected model rates

meeting_time_zones

Shared 30-minute slots within 09:00–17:00 for 2–8 people

recurring_schedule

Monthly hours, recurrence rules and an RFC 5545 calendar

ai_subscription_stack_cost

Monthly and annual totals with overlapping capabilities

cron_next_runs

1–10 matches after a UTC instant, within 366 days

The justfile installs frozen dependencies, checks prerequisites and runs the build and tests:

just setup
just doctor
just check

Self-hosting

For checkout development, run just setup to install Node 26 and pnpm 12. The published package supports Node.js 22.19 or newer.

git clone https://github.com/OperatorNest/mcp-tools.git
cd mcp-tools
pnpm install --frozen-lockfile
pnpm test:local
pnpm build
node dist/stdio.js

For a client with stdio support, use node with the absolute path to dist/stdio.js as its argument to serve newline-delimited MCP messages on stdin/stdout, keeping protocol traffic separate from the logs written to stderr.

The package is prepared as @operatornest/mcp-tools version 1.1.0. To run a local package through npx before registry publication:

pnpm pack --out /tmp/operatornest-mcp-tools-1.1.0.tgz
npx --yes --package /tmp/operatornest-mcp-tools-1.1.0.tgz operatornest-mcp-tools

After npm publication, the equivalent command is npx --yes @operatornest/mcp-tools@1.1.0. Publication is a separate maintainer action.

HTTP Worker

src/worker.ts exports a standalone Worker with an /mcp endpoint. Use your own Worker configuration; wrangler.jsonc is a local starting point. Run it locally with:

pnpm dev:worker --port 8787

Connect a client to http://localhost:8787/mcp. For remote hosting, follow the Worker setup documentation in your own account.

The HTTP handler uses stateless JSON responses without sessions or subscription streams, caps request bodies at 32 KiB, rejects JSON-RPC batches and returns generic errors, with CORS for HTTPS origins and local-origin access to local endpoints.

Rate limiting is optional. To enable it, configure an MCP_LIMITER rate-limit binding. When present, it uses a SHA-256 hash of CF-Connecting-IP; rejection returns HTTP 429 with Retry-After: 60. Missing client IP or a binding error returns HTTP 503. No binding means no rate limiting.

Related MCP server: Cron Parser API

Client setup

These snippets connect to the hosted endpoint. Substitute your own HTTPS /mcp URL to use your HTTP instance. Setup documentation checked on 2 October 2026; account and workspace controls may affect tool access.

ChatGPT

Enable Developer mode in Settings → Security and login. In Plugins, use the plus button to create a developer-mode app with this URL and No Authentication:

https://operatornest.com/mcp

Select the app from Developer mode in the conversation's plus menu. Official instructions.

Claude

In Claude, open Customize → Connectors, select Add custom connector, and enter https://operatornest.com/mcp. Choose No sign in and add the connector. Enable it for your conversation from the plus menu's Connectors list. Organization owners may need to add it first. Official connector instructions.

For Claude Code:

claude mcp add --transport http operatornest https://operatornest.com/mcp

Check the connection with /mcp. Official instructions.

Codex

codex mcp add operatornest --url https://operatornest.com/mcp

Alternatively, in ~/.codex/config.toml:

[mcp_servers.operatornest]
url = "https://operatornest.com/mcp"

Official instructions.

Cursor

Add to .cursor/mcp.json in your project, or ~/.cursor/mcp.json for all projects:

{
  "mcpServers": {
    "operatornest": { "url": "https://operatornest.com/mcp" }
  }
}

Official instructions.

Gemini CLI

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "operatornest": { "httpUrl": "https://operatornest.com/mcp" }
  }
}

Official instructions.

VS Code

Add .vscode/mcp.json to your project:

{
  "servers": {
    "operatornest": { "type": "http", "url": "https://operatornest.com/mcp" }
  }
}

Start the server from the configuration file and enable its tools in Agent mode. Official instructions.

Data and limits

API rates are frozen at 2026-09-28T17:08:16.340Z in src/data/pricing-snapshot.json, containing 194 models from models.dev. This is the hosted MCP's filtered snapshot. Use the bundled modelId values; the broader website catalog can include records this server does not accept. Null rates stay unlisted. Caching falls back to the input rate when absent; batch discounts require published data. Non-token charges are excluded.

Subscription plans are in src/data/ai-plans.ts, checked on 27 September 2026 with official source links. Annual totals use published annual charges, or twelve monthly charges when no annual charge is listed. Taxes, regional differences and promotions are excluded.

Meeting and cron results use the runtime's IANA time-zone database. Recurring calendars use floating local times in the importing calendar. Cron supports numeric stars, lists, ranges, steps and weekday names across GitHub, Cloudflare, Quartz and AWS dialects; L, W, # and named months are rejected. Results describe estimates and schedule previews.

Development

pnpm check
pnpm test:local
pnpm build
pnpm dlx @modelcontextprotocol/inspector --cli node dist/stdio.js \
  --method tools/call --tool-name cron_next_runs \
  --tool-arg 'expression=0 9 * * 1-5' --tool-arg dialect=github \
  --tool-arg zone=UTC --tool-arg after=2026-10-02T00:00:00Z --tool-arg count=1

Tests validate input and output schemas, valid and invalid calls, HTTP limits, and initialize/list/call on both transports. See Inspector CLI documentation, contribution guidance, security reporting and data attribution.

MIT. Copyright (c) 2026 OperatorNest.

Available Tools

5 tools
ai_api_costAI API costA
Read-onlyIdempotent
Inspect

Estimate API workload costs in USD per request, day and month, with rates and dated snapshot provenance. Use for token budgets; use ai_subscription_stack_cost for chat or coding subscriptions. Model IDs use providerId/id from https://operatornest.com/api/models?subset=pricing, filtered to the MCP catalog; the OSS bundle lists accepted IDs in src/data/pricing-snapshot.json. Rates stay offline until the catalog is updated; missing rates return null. Cached tokens are part of total input; published batch and long-context rates apply only when eligible. Non-token charges are excluded.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelIdsYesUnique providerId/id values from the MCP pricing catalog. Unknown or unavailable IDs fail validation.
inputTokensYesTotal input tokens per request, including cached input tokens.
outputTokensYesGenerated output tokens per request.
batchModelIdsNoOptional subset of modelIds to price with published batch discounts. Omission or [] uses standard rates; IDs without a published discount are rejected.
requestsPerDayYesRequests used to scale the daily estimate, independent of requestsPerMonth.
requestsPerMonthYesRequests used to scale the monthly estimate; not inferred from the daily count.
cachedInputTokensYesCached portion of inputTokens per request; must not exceed inputTokens. Use 0 without caching.

Output Schema

ParametersJSON Schema
NameRequiredDescription
toolYesCalculator identifier for this result.
inputYesNormalized inputs used for this calculation.
unitsYesUnits for the numeric and time fields in this result.
methodYesCalculation or ranking method applied to the inputs.
estimatesYesCost estimates in selected-model order.
provenanceYesDated data sources or runtime time-zone information used for this result.
assumptionsYesLimits and assumptions to retain when presenting the result.

TDQS

A4.7/5.0
Behavior5/5

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

Annotations declare a safe, offline, idempotent read, and the description adds real behavioral context beyond them: rates stay offline until the catalog updates, missing rates return null, cached tokens count inside total input, batch/long-context rates apply only when eligible, and non-token charges are excluded. These are exactly the operational caveats an agent needs to interpret results.

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-loads the core purpose before caveats, and every sentence carries information. Some sentences bundle several distinct caveats (cached tokens + batch rates + non-token charges), which makes it dense but not padded.

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?

Covers provenance, failure behavior (null on missing rates), and pricing-eligibility edge cases for a 7-parameter estimation tool, and an output schema exists so return shape need not be described. Minor gaps remain around how the per-day/month windows are defined and whether zero-request inputs are valid.

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 description coverage is already 100%, so the baseline is 3. The description adds cross-field meaning the schema does not spell out: modelIds follow providerId/id from a specific catalog, rates are dated snapshots, and batch eligibility is conditional. It stops short of explaining the interaction between requestsPerDay and requestsPerMonth beyond what the schema already states.

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 (Estimate), resource (API workload costs), unit (USD), and scope (per request, day, month), plus provenance. It explicitly distinguishes itself from the sibling ai_subscription_stack_cost, so an agent can route between them without opening a schema.

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?

Gives an explicit positive trigger (token budgets) and a named alternative with the condition that selects it (ai_subscription_stack_cost for chat or coding subscriptions). It also tells the agent where valid model IDs come from (the pricing catalog endpoint / OSS snapshot file).

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

ai_subscription_stack_costAI subscription stack costA
Read-onlyIdempotent
Inspect

Total selected AI chat and coding subscriptions in USD and identify overlapping capabilities. Use to review a subscription stack; use ai_api_cost for API token charges. Select unique planIds from the schema enum; [] returns zero totals and no plans. Returns monthly and annual totals, selected plans, capability groups and dated official sources. Annual totals use published annual billing or twelve monthly charges; taxes, regional differences and promotions are excluded. Bundled rates are dated estimates, without live billing lookup or subscription changes.

ParametersJSON Schema
NameRequiredDescriptionDefault
planIdsYesUnique subscription IDs from the enum. An empty list returns zero totals and no selected plans.

Output Schema

ParametersJSON Schema
NameRequiredDescription
toolYesCalculator identifier for this result.
inputYesNormalized inputs used for this calculation.
plansYesSelected plans with published USD charges and dated sources, in input order.
unitsYesUnits for the numeric and time fields in this result.
methodYesCalculation or ranking method applied to the inputs.
overlapYesCapability groups and selected plan IDs; more than one plan ID indicates overlap.
provenanceYesDated data sources or runtime time-zone information used for this result.
annualTotalYesSum of published annual charges or twelve monthly charges per plan; excludes taxes, regional changes and promotions.
assumptionsYesLimits and assumptions to retain when presenting the result.
monthlyTotalYesSum of selected monthly USD charges; zero for an empty stack.

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations (which only cover read-only/idempotent/no-write): it discloses how annual totals are derived, that taxes/regional differences/promotions are excluded, that bundled rates are dated estimates, and that no live billing lookup or subscription mutation occurs. That is exactly the behavioral context an agent needs before quoting numbers to a user.

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?

Five dense sentences with no filler, and the primary purpose plus sibling routing are front-loaded. It is information-heavy and could use light grouping, but every sentence carries operational information.

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?

An output schema exists, so return values need not be described, yet the description still sketches the return shape (totals, selected plans, capability groups, dated sources) and bounds the accuracy of its numbers. Nothing material is missing for invoking this correctly.

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% and the enum already enumerates valid planIds, so the baseline is 3. The description adds genuine meaning beyond the schema: the 'unique' constraint, the empty-list semantics ('[] returns zero totals'), and the requirement to select IDs from the enum rather than free-text plan names.

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+resource (compute total cost of selected AI chat/coding subscriptions) plus the analytical add-on (identify overlapping capabilities). It explicitly distinguishes itself from the sibling ai_api_cost, so an agent can route without opening either schema.

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?

Names the scenario ('use to review a subscription stack') and the alternative with its condition ('use ai_api_cost for API token charges'). It also covers the degenerate input case ('[] returns zero totals and no plans'), leaving little to inference.

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

cron_next_runsCron next runsA
Read-onlyIdempotent
Inspect

Preview up to 10 cron matches strictly after a supplied UTC instant, within a 366-day search. Use to check existing scheduler syntax; use recurring_schedule to draft task recurrence calendars or meeting_time_zones for participant overlap. Returns UTC starts, local labels, normalized inputs and a dated syntax source; fewer matches or [] means the search window ended. Supports numeric stars, lists, ranges, steps and weekday names in the selected dialect; rejects L, W, # and named months. cloudflare requires UTC; other zones follow runtime daylight saving transitions. No schedule is installed or run.

ParametersJSON Schema
NameRequiredDescriptionDefault
zoneYesIANA time zone for matching local cron fields. cloudflare requires UTC. Daylight saving transitions follow the runtime time-zone database.
afterYesUTC ISO instant from 2000 through 2100; matches are strictly after this instant. Only Z offsets are accepted.
countYesMaximum matches to return. The list may be shorter or empty if no further matches occur within the 366-day search.
dialectYesScheduler syntax and weekday numbering. github uses 0 or 7 for Sunday and 1–6 for Monday–Saturday; the others use 1–7 for Sunday–Saturday.
expressionYesCron fields in the selected dialect: five for github/cloudflare, six or seven for quartz, six for aws (optional cron(...) wrapper). Supports *, lists, ranges, steps and weekday names; rejects L, W, # and named months. Quartz/aws require ? in exactly one day field.

Output Schema

ParametersJSON Schema
NameRequiredDescription
runsYesChronological cron matches strictly after after, up to count; may be shorter or empty within the search window.
toolYesCalculator identifier for this result.
inputYesNormalized inputs used for this calculation.
methodYesCalculation or ranking method applied to the inputs.
provenanceYesDated data sources or runtime time-zone information used for this result.
searchDaysYesMaximum search window in days.
assumptionsYesLimits and assumptions to retain when presenting the result.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, and the description adds substantial extra context: no schedule is installed or run, the 366-day window bound, that fewer matches or [] means the window ended, dialect-specific rejection rules (L, W, #, named months), and that cloudflare requires UTC while other zones follow runtime DST transitions.

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?

Purpose and window bound are front-loaded, and each subsequent sentence carries a distinct constraint (dialect limits, zone rules, no side effects). It is dense but not padded, though the return-shape sentence is partly redundant with the output schema.

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 read-only preview tool with full schema coverage and an output schema, the description covers everything an agent needs: what is matched, the search bound, dialect/zone caveats, and the absence of side effects. The return-value sentence is extra but harmless.

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% and the schema already documents dialect numbering, the ? requirement for quartz/aws, the Z-only constraint on 'after', and the 366-day/count semantics. The description largely restates these ('Supports numeric stars, lists, ranges, steps and weekday names... rejects L, W, # and named months'), so it earns the baseline 3 rather than more.

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 ('Preview up to 10 cron matches strictly after a supplied UTC instant, within a 366-day search') and explicitly distinguishes itself from siblings recurring_schedule and meeting_time_zones by naming what each of those is for instead.

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?

Gives explicit when-to-use ('Use to check existing scheduler syntax') plus named alternatives with their selecting conditions ('recurring_schedule to draft task recurrence calendars or meeting_time_zones for participant overlap'), so routing is unambiguous.

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

meeting_time_zonesMeeting time zonesA
Read-onlyIdempotent
Inspect

Find shared 30-minute meeting slots inside 09:00–17:00 for 2–8 participants. Use to compare workday overlap; use recurring_schedule for repeating task calendars or cron_next_runs for scheduler previews. Returns all candidates, overlap count and up to three best slots ranked nearest to each person’s 13:00, with UTC starts and local labels. The date belongs to the first participant’s zone; daylight saving uses runtime IANA data. No calendar availability or holiday lookup, invitations or calendar writes.

ParametersJSON Schema
NameRequiredDescriptionDefault
dateYesMeeting date in the first person’s local time zone, from 2000-01-01 to 2100-12-31.
peopleYesParticipants in display order. The first person determines the local date; all must fit a full half-hour inside 09:00–17:00.

Output Schema

ParametersJSON Schema
NameRequiredDescription
rowsYesAll candidate half-hour starts on the first participant’s local date, in chronological order.
toolYesCalculator identifier for this result.
inputYesNormalized inputs used for this calculation.
unitsYesUnits for the numeric and time fields in this result.
methodYesCalculation or ranking method applied to the inputs.
bestSlotsYesUp to three shared slots ranked by score, then earliest UTC start; [] means no overlap.
provenanceYesDated data sources or runtime time-zone information used for this result.
assumptionsYesLimits and assumptions to retain when presenting the result.
overlapCountYesNumber of candidate slots inside every participant’s workday.

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive, non-open-world behavior, so the safety profile is covered. The description adds real behavioral context beyond that: DST resolved via runtime IANA data, the date belonging to the first participant's zone, and the ranking heuristic (nearest each person's 13:00). Slightly short of 5 only because pagination/limits on candidate count aren't addressed.

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

Conciseness5/5

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

Front-loaded with the core purpose, then alternatives, then return shape and edge cases. Four tight sentences, each carrying distinct information with no redundancy or filler.

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?

An output schema exists so return values needn't be re-explained, and annotations cover safety. The description still fills the remaining gaps an agent needs – DST handling, date-zone anchoring, ranking rule, and explicit out-of-scope operations – making it complete for a two-parameter read tool.

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 and the schema carries the syntax. The description nonetheless reinforces semantics that matter for interpretation – that the date is anchored to the first participant's zone and that participants are ordered with the first determining the local date – which clarifies intent beyond raw field definitions.

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 (Find) and resource (shared 30-minute meeting slots) with concrete scope: 09:00–17:00 window and 2–8 participants. It explicitly names sibling tools (recurring_schedule, cron_next_runs) so the agent can distinguish it without opening any schema.

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?

Gives positive guidance ("Use to compare workday overlap") and routes to alternatives by condition (recurring_schedule for repeating task calendars, cron_next_runs for scheduler previews). It also states what it is not for: calendar availability, holiday lookup, invitations, or calendar writes.

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

recurring_scheduleRecurring scheduleA
Read-onlyIdempotent
Inspect

Prepare weekly, biweekly or monthly task calendars and estimate monthly effort for up to 20 tasks. Use to draft a recurring work plan; use cron_next_runs to preview existing cron syntax or meeting_time_zones for shared workday slots. Returns monthly hours, first dates, recurrence rules and an RFC 5545 calendar. Times float in the importing calendar’s local zone; weekly estimates use 52/12 runs per month and biweekly 26/12. owner is a planning label, with no assignment or execution. No calendar is updated; an empty task list returns zero hours and no events.

ParametersJSON Schema
NameRequiredDescriptionDefault
tasksYesTasks to include in the estimate and calendar. [] returns zero hours and a calendar with no events.
startDateYesEarliest date for the first occurrence of each task, from 2000-01-01 to 2100-12-31.

Output Schema

ParametersJSON Schema
NameRequiredDescription
icsYesRFC 5545 calendar with CRLF folding and floating local times.
toolYesCalculator identifier for this result.
inputYesNormalized inputs used for this calculation.
unitsYesUnits for the numeric and time fields in this result.
methodYesCalculation or ranking method applied to the inputs.
schedulesYesNormalized tasks with their first occurrence and recurrence rule, in input order.
provenanceYesDated data sources or runtime time-zone information used for this result.
assumptionsYesLimits and assumptions to retain when presenting the result.
monthlyHoursYesEstimated monthly hours using 52/12 weekly, 26/12 biweekly and one monthly run.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes further: 'No calendar is updated', empty task list yields zero hours and no events, times float in the importing calendar's local zone, and owner is only a planning label with no assignment or execution. It also discloses the estimation math (52/12 weekly, 26/12 biweekly), which no annotation or schema field conveys.

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?

Five tight sentences, front-loaded with the primary action and scope before alternatives and caveats; every sentence carries distinct information (alternatives, return shape, time semantics, estimation math, no-side-effect guarantee). Dense but not padded, though the return-value sentence overlaps with the output schema.

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 2-parameter tool with full schema coverage and an output schema, this covers everything an agent needs: what it produces, how effort is estimated, time-zone behavior, side-effect absence, and the empty-input edge case. Nothing material is missing.

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 and the schema already documents day/monthday/time/owner semantics. The description still adds value the schema does not: the 52/12 and 26/12 runs-per-month estimation formula and the floating-time-zone interpretation of the produced times, which is what an agent needs to predict output. Slightly above baseline.

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 ('Prepare... estimate') and resource ('weekly, biweekly or monthly task calendars'), plus the scope bound of 20 tasks. It names siblings cron_next_runs and meeting_time_zones so the agent can separate this planning tool from the cron-preview and timezone tools without opening a schema.

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?

Explicitly says to use it 'to draft a recurring work plan' and routes to alternatives by condition: cron_next_runs for existing cron syntax, meeting_time_zones for shared workday slots. When-to-use and which-alternative are both stated, not inferred.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 5 tool updatesv1.1.0
    • Changedai_api_cost53 fields changed
      • changedInput schema / properties / batchModelIds / description
        Previous value: -"Optional model IDs using a published batch discount."New value: +"Optional subset of modelIds to price with published batch discounts. Omission or [] uses standard rates; IDs without a published discount are rejected."
      • addedInput schema / properties / batchModelIds / examples
        Added value: +[
+  []
+]
      • addedInput schema / properties / batchModelIds / items / description
        Added value: +"Selected model ID with a published batch discount."
      • addedInput schema / properties / cachedInputTokens / description
        Added value: +"Cached portion of inputTokens per request; must not exceed inputTokens. Use 0 without caching."
      • addedInput schema / properties / cachedInputTokens / examples
        Added value: +[
+  5000
+]
      • addedInput schema / properties / inputTokens / description
        Added value: +"Total input tokens per request, including cached input tokens."
      • addedInput schema / properties / inputTokens / examples
        Added value: +[
+  10000
+]
      • addedInput schema / properties / modelIds / description
        Added value: +"Unique providerId/id values from the MCP pricing catalog. Unknown or unavailable IDs fail validation."
      • addedInput schema / properties / modelIds / items / description
        Added value: +"Model ID accepted by the MCP pricing catalog."
      • addedInput schema / properties / outputTokens / description
        Added value: +"Generated output tokens per request."
      • addedInput schema / properties / outputTokens / examples
        Added value: +[
+  2000
+]
      • addedInput schema / properties / requestsPerDay / description
        Added value: +"Requests used to scale the daily estimate, independent of requestsPerMonth."
      • addedInput schema / properties / requestsPerDay / examples
        Added value: +[
+  100
+]
      • addedInput schema / properties / requestsPerMonth / description
        Added value: +"Requests used to scale the monthly estimate; not inferred from the daily count."
      • addedInput schema / properties / requestsPerMonth / examples
        Added value: +[
+  3000
+]
      • addedOutput schema / description
        Added value: +"API token cost estimates with normalized inputs, USD units, rate assumptions and catalog snapshot provenance."
      • addedOutput schema / properties / assumptions / description
        Added value: +"Limits and assumptions to retain when presenting the result."
      • addedOutput schema / properties / estimates / description
        Added value: +"Cost estimates in selected-model order."
      • addedOutput schema / properties / estimates / items / properties / batch / description
        Added value: +"Whether a requested published batch discount was applied."
      • addedOutput schema / properties / estimates / items / properties / longContext / description
        Added value: +"Whether published long-context rate multipliers apply."
      • addedOutput schema / properties / estimates / items / properties / modelId / description
        Added value: +"Selected providerId/id from the pricing catalog."
      • addedOutput schema / properties / estimates / items / properties / name / description
        Added value: +"Display name of the selected model or plan."
      • addedOutput schema / properties / estimates / items / properties / note / description
        Added value: +"Catalog note about pricing limitations."
      • addedOutput schema / properties / estimates / items / properties / perDay / description
        Added value: +"Estimated USD per day at requestsPerDay; null when rates are unlisted."
      • addedOutput schema / properties / estimates / items / properties / perMonth / description
        Added value: +"Estimated USD per month at requestsPerMonth; null when rates are unlisted."
      • addedOutput schema / properties / estimates / items / properties / perRequest / description
        Added value: +"Estimated USD per request; null when any required rate is unlisted."
      • addedOutput schema / properties / estimates / items / properties / ratesPerMillion / description
        Added value: +"USD rates per million tokens after long-context multipliers, before batch discounts; null means unlisted."
      • addedOutput schema / properties / estimates / items / properties / ratesPerMillion / properties / cachedInput / description
        Added value: +"Cached-input USD rate per million tokens; falls back to the input rate when absent."
      • addedOutput schema / properties / estimates / items / properties / ratesPerMillion / properties / input / description
        Added value: +"Uncached-input USD rate per million tokens; null means unlisted."
      • addedOutput schema / properties / estimates / items / properties / ratesPerMillion / properties / output / description
        Added value: +"Output USD rate per million tokens; null means unlisted."
      • addedOutput schema / properties / estimates / items / properties / sourceUrl / description
        Added value: +"Official rate or scheduler syntax reference URL."
      • addedOutput schema / properties / input / description
        Added value: +"Normalized inputs used for this calculation."
      • changedOutput schema / properties / input / properties / batchModelIds / description
        Previous value: -"Optional model IDs using a published batch discount."New value: +"Optional subset of modelIds to price with published batch discounts. Omission or [] uses standard rates; IDs without a published discount are rejected."
      • addedOutput schema / properties / input / properties / batchModelIds / examples
        Added value: +[
+  []
+]
      • addedOutput schema / properties / input / properties / batchModelIds / items / description
        Added value: +"Selected model ID with a published batch discount."
      • addedOutput schema / properties / input / properties / cachedInputTokens / description
        Added value: +"Cached portion of inputTokens per request; must not exceed inputTokens. Use 0 without caching."
      • addedOutput schema / properties / input / properties / cachedInputTokens / examples
        Added value: +[
+  5000
+]
      • addedOutput schema / properties / input / properties / inputTokens / description
        Added value: +"Total input tokens per request, including cached input tokens."
      • addedOutput schema / properties / input / properties / inputTokens / examples
        Added value: +[
+  10000
+]
      • addedOutput schema / properties / input / properties / modelIds / description
        Added value: +"Unique providerId/id values from the MCP pricing catalog. Unknown or unavailable IDs fail validation."
      • addedOutput schema / properties / input / properties / modelIds / items / description
        Added value: +"Model ID accepted by the MCP pricing catalog."
      • addedOutput schema / properties / input / properties / outputTokens / description
        Added value: +"Generated output tokens per request."
      • addedOutput schema / properties / input / properties / outputTokens / examples
        Added value: +[
+  2000
+]
      • addedOutput schema / properties / input / properties / requestsPerDay / description
        Added value: +"Requests used to scale the daily estimate, independent of requestsPerMonth."
      • addedOutput schema / properties / input / properties / requestsPerDay / examples
        Added value: +[
+  100
+]
      • addedOutput schema / properties / input / properties / requestsPerMonth / description
        Added value: +"Requests used to scale the monthly estimate; not inferred from the daily count."
      • addedOutput schema / properties / input / properties / requestsPerMonth / examples
        Added value: +[
+  3000
+]
      • addedOutput schema / properties / method / description
        Added value: +"Calculation or ranking method applied to the inputs."
      • addedOutput schema / properties / provenance / additionalProperties / description
        Added value: +"Unit or source detail for the named field."
      • addedOutput schema / properties / provenance / description
        Added value: +"Dated data sources or runtime time-zone information used for this result."
      • addedOutput schema / properties / tool / description
        Added value: +"Calculator identifier for this result."
      • addedOutput schema / properties / units / additionalProperties / description
        Added value: +"Unit or source detail for the named field."
      • addedOutput schema / properties / units / description
        Added value: +"Units for the numeric and time fields in this result."
    • Changedai_subscription_stack_cost39 fields changed
      • addedInput schema / properties / planIds / description
        Added value: +"Unique subscription IDs from the enum. An empty list returns zero totals and no selected plans."
      • addedInput schema / properties / planIds / examples
        Added value: +[
+  [
+    "chatgpt-plus",
+    "claude-pro"
+  ],
+  []
+]
      • addedInput schema / properties / planIds / items / description
        Added value: +"ID of a plan in the bundled subscription catalog."
      • addedOutput schema / description
        Added value: +"Subscription totals, capability overlap and dated plan sources with normalized selection."
      • addedOutput schema / properties / annualTotal / description
        Added value: +"Sum of published annual charges or twelve monthly charges per plan; excludes taxes, regional changes and promotions."
      • addedOutput schema / properties / assumptions / description
        Added value: +"Limits and assumptions to retain when presenting the result."
      • addedOutput schema / properties / input / description
        Added value: +"Normalized inputs used for this calculation."
      • addedOutput schema / properties / input / properties / planIds / description
        Added value: +"Unique subscription IDs from the enum. An empty list returns zero totals and no selected plans."
      • addedOutput schema / properties / input / properties / planIds / examples
        Added value: +[
+  [
+    "chatgpt-plus",
+    "claude-pro"
+  ],
+  []
+]
      • addedOutput schema / properties / input / properties / planIds / items / description
        Added value: +"ID of a plan in the bundled subscription catalog."
      • addedOutput schema / properties / method / description
        Added value: +"Calculation or ranking method applied to the inputs."
      • addedOutput schema / properties / monthlyTotal / description
        Added value: +"Sum of selected monthly USD charges; zero for an empty stack."
      • addedOutput schema / properties / overlap / description
        Added value: +"Capability groups and selected plan IDs; more than one plan ID indicates overlap."
      • addedOutput schema / properties / overlap / items / properties / id / description
        Added value: +"Catalog identifier for a plan or capability."
      • addedOutput schema / properties / overlap / items / properties / label / description
        Added value: +"Human-readable capability label."
      • addedOutput schema / properties / overlap / items / properties / planIds / description
        Added value: +"Selected plans offering this capability; more than one ID indicates overlap."
      • addedOutput schema / properties / plans / description
        Added value: +"Selected plans with published USD charges and dated sources, in input order."
      • addedOutput schema / properties / plans / items / properties / annual / description
        Added value: +"Published USD annual charge; null if only monthly billing is listed."
      • addedOutput schema / properties / plans / items / properties / annualNote / description
        Added value: +"Qualification about annual billing."
      • addedOutput schema / properties / plans / items / properties / capabilities / additionalProperties / description
        Added value: +"Whether the plan offers this capability."
      • addedOutput schema / properties / plans / items / properties / capabilities / description
        Added value: +"Capability IDs mapped to whether the selected plan includes them."
      • addedOutput schema / properties / plans / items / properties / checked / description
        Added value: +"Date the referenced catalog or scheduler source was checked."
      • addedOutput schema / properties / plans / items / properties / id / description
        Added value: +"Catalog identifier for a plan or capability."
      • addedOutput schema / properties / plans / items / properties / modelFamilies / description
        Added value: +"Model family labels listed for the plan."
      • addedOutput schema / properties / plans / items / properties / modelSource / description
        Added value: +"Official source for plan model access."
      • addedOutput schema / properties / plans / items / properties / monthly / description
        Added value: +"Published USD monthly charge."
      • addedOutput schema / properties / plans / items / properties / name / description
        Added value: +"Display name of the selected model or plan."
      • addedOutput schema / properties / plans / items / properties / provider / description
        Added value: +"Public subscription provider name."
      • addedOutput schema / properties / plans / items / properties / source / description
        Added value: +"Official plan pricing URL."
      • addedOutput schema / properties / plans / items / properties / sourceNote / description
        Added value: +"Qualification about the source or plan availability."
      • addedOutput schema / properties / provenance / description
        Added value: +"Dated data sources or runtime time-zone information used for this result."
      • addedOutput schema / properties / provenance / properties / checked / description
        Added value: +"Date the referenced catalog or scheduler source was checked."
      • addedOutput schema / properties / provenance / properties / sources / description
        Added value: +"Official pricing sources for the selected plans."
      • addedOutput schema / properties / provenance / properties / sources / items / properties / checked / description
        Added value: +"Date the referenced catalog or scheduler source was checked."
      • addedOutput schema / properties / provenance / properties / sources / items / properties / planId / description
        Added value: +"Selected plan ID corresponding to this source."
      • addedOutput schema / properties / provenance / properties / sources / items / properties / url / description
        Added value: +"Official plan pricing URL."
      • addedOutput schema / properties / tool / description
        Added value: +"Calculator identifier for this result."
      • addedOutput schema / properties / units / description
        Added value: +"Units for the numeric and time fields in this result."
      • addedOutput schema / properties / units / properties / totals / description
        Added value: +"Currency for subscription totals."
    • Changedcron_next_runs38 fields changed
      • changedInput schema / properties / after / description
        Previous value: -"UTC ISO instant from 2000 through 2100; matches are strictly after this instant."New value: +"UTC ISO instant from 2000 through 2100; matches are strictly after this instant. Only Z offsets are accepted."
      • addedInput schema / properties / after / examples
        Added value: +[
+  "2026-10-02T00:00:00Z"
+]
      • changedInput schema / properties / after / maxLength
        Previous value: -30New value: +24
      • addedInput schema / properties / after / minLength
        Added value: +20
      • addedInput schema / properties / after / pattern
        Added value: +"^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}(?:\\.\\d{1,3})?Z$"
      • addedInput schema / properties / count / description
        Added value: +"Maximum matches to return. The list may be shorter or empty if no further matches occur within the 366-day search."
      • addedInput schema / properties / count / examples
        Added value: +[
+  3
+]
      • addedInput schema / properties / dialect / description
        Added value: +"Scheduler syntax and weekday numbering. github uses 0 or 7 for Sunday and 1–6 for Monday–Saturday; the others use 1–7 for Sunday–Saturday."
      • addedInput schema / properties / dialect / examples
        Added value: +[
+  "github"
+]
      • addedInput schema / properties / expression / description
        Added value: +"Cron fields in the selected dialect: five for github/cloudflare, six or seven for quartz, six for aws (optional cron(...) wrapper). Supports *, lists, ranges, steps and weekday names; rejects L, W, # and named months. Quartz/aws require ? in exactly one day field."
      • addedInput schema / properties / expression / examples
        Added value: +[
+  "0 9 * * 1-5"
+]
      • addedInput schema / properties / zone / description
        Added value: +"IANA time zone for matching local cron fields. cloudflare requires UTC. Daylight saving transitions follow the runtime time-zone database."
      • addedInput schema / properties / zone / examples
        Added value: +[
+  "UTC",
+  "America/New_York"
+]
      • addedOutput schema / description
        Added value: +"Bounded cron preview with normalized syntax, UTC starts, local labels and scheduler source."
      • addedOutput schema / properties / assumptions / description
        Added value: +"Limits and assumptions to retain when presenting the result."
      • addedOutput schema / properties / input / description
        Added value: +"Normalized inputs used for this calculation."
      • changedOutput schema / properties / input / properties / after / description
        Previous value: -"UTC ISO instant from 2000 through 2100; matches are strictly after this instant."New value: +"UTC ISO instant from 2000 through 2100; matches are strictly after this instant. Only Z offsets are accepted."
      • addedOutput schema / properties / input / properties / after / examples
        Added value: +[
+  "2026-10-02T00:00:00Z"
+]
      • changedOutput schema / properties / input / properties / after / maxLength
        Previous value: -30New value: +24
      • addedOutput schema / properties / input / properties / after / minLength
        Added value: +20
      • addedOutput schema / properties / input / properties / after / pattern
        Added value: +"^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}(?:\\.\\d{1,3})?Z$"
      • addedOutput schema / properties / input / properties / count / description
        Added value: +"Maximum matches to return. The list may be shorter or empty if no further matches occur within the 366-day search."
      • addedOutput schema / properties / input / properties / count / examples
        Added value: +[
+  3
+]
      • addedOutput schema / properties / input / properties / dialect / description
        Added value: +"Scheduler syntax and weekday numbering. github uses 0 or 7 for Sunday and 1–6 for Monday–Saturday; the others use 1–7 for Sunday–Saturday."
      • addedOutput schema / properties / input / properties / dialect / examples
        Added value: +[
+  "github"
+]
      • addedOutput schema / properties / input / properties / expression / description
        Added value: +"Cron fields in the selected dialect: five for github/cloudflare, six or seven for quartz, six for aws (optional cron(...) wrapper). Supports *, lists, ranges, steps and weekday names; rejects L, W, # and named months. Quartz/aws require ? in exactly one day field."
      • addedOutput schema / properties / input / properties / expression / examples
        Added value: +[
+  "0 9 * * 1-5"
+]
      • addedOutput schema / properties / input / properties / zone / description
        Added value: +"IANA time zone for matching local cron fields. cloudflare requires UTC. Daylight saving transitions follow the runtime time-zone database."
      • addedOutput schema / properties / input / properties / zone / examples
        Added value: +[
+  "UTC",
+  "America/New_York"
+]
      • addedOutput schema / properties / method / description
        Added value: +"Calculation or ranking method applied to the inputs."
      • addedOutput schema / properties / provenance / description
        Added value: +"Dated data sources or runtime time-zone information used for this result."
      • addedOutput schema / properties / provenance / properties / checked / description
        Added value: +"Date the referenced catalog or scheduler source was checked."
      • addedOutput schema / properties / provenance / properties / sourceUrl / description
        Added value: +"Official rate or scheduler syntax reference URL."
      • addedOutput schema / properties / runs / description
        Added value: +"Chronological cron matches strictly after after, up to count; may be shorter or empty within the search window."
      • addedOutput schema / properties / runs / items / properties / label / description
        Added value: +"Start formatted in the requested IANA time zone."
      • addedOutput schema / properties / runs / items / properties / startUtc / description
        Added value: +"Start instant in ISO 8601 UTC."
      • addedOutput schema / properties / searchDays / description
        Added value: +"Maximum search window in days."
      • addedOutput schema / properties / tool / description
        Added value: +"Calculator identifier for this result."
    • Changedmeeting_time_zones38 fields changed
      • changedInput schema / properties / date / description
        Previous value: -"Real date from 2000-01-01 to 2100-12-31."New value: +"Meeting date in the first person’s local time zone, from 2000-01-01 to 2100-12-31."
      • addedInput schema / properties / date / examples
        Added value: +[
+  "2026-10-05"
+]
      • addedInput schema / properties / date / maxLength
        Added value: +10
      • addedInput schema / properties / date / minLength
        Added value: +10
      • addedInput schema / properties / people / description
        Added value: +"Participants in display order. The first person determines the local date; all must fit a full half-hour inside 09:00–17:00."
      • addedInput schema / properties / people / items / properties / name / description
        Added value: +"Participant label used in the returned local-time display."
      • addedInput schema / properties / people / items / properties / name / examples
        Added value: +[
+  "Sam"
+]
      • changedInput schema / properties / people / items / properties / zone / description
        Previous value: -"An IANA time zone supported by Intl.DateTimeFormat, such as America/New_York."New value: +"IANA time zone supported by Intl.DateTimeFormat."
      • addedInput schema / properties / people / items / properties / zone / examples
        Added value: +[
+  "America/New_York",
+  "Asia/Kolkata"
+]
      • addedOutput schema / description
        Added value: +"Meeting candidates and ranked shared slots with normalized participants, local labels and DST assumptions."
      • addedOutput schema / properties / assumptions / description
        Added value: +"Limits and assumptions to retain when presenting the result."
      • addedOutput schema / properties / bestSlots / description
        Added value: +"Up to three shared slots ranked by score, then earliest UTC start; [] means no overlap."
      • addedOutput schema / properties / bestSlots / items / properties / inside / description
        Added value: +"Whether each participant’s full half-hour fits their 09:00–17:00 workday, in input order."
      • addedOutput schema / properties / bestSlots / items / properties / labels / description
        Added value: +"Local start labels for participants in input order."
      • addedOutput schema / properties / bestSlots / items / properties / score / description
        Added value: +"Sum of absolute hours from 13:00 at each participant’s slot midpoint; lower ranks first."
      • addedOutput schema / properties / bestSlots / items / properties / startUtc / description
        Added value: +"Start instant in ISO 8601 UTC."
      • addedOutput schema / properties / input / description
        Added value: +"Normalized inputs used for this calculation."
      • changedOutput schema / properties / input / properties / date / description
        Previous value: -"Real date from 2000-01-01 to 2100-12-31."New value: +"Meeting date in the first person’s local time zone, from 2000-01-01 to 2100-12-31."
      • addedOutput schema / properties / input / properties / date / examples
        Added value: +[
+  "2026-10-05"
+]
      • addedOutput schema / properties / input / properties / date / maxLength
        Added value: +10
      • addedOutput schema / properties / input / properties / date / minLength
        Added value: +10
      • addedOutput schema / properties / input / properties / people / description
        Added value: +"Participants in display order. The first person determines the local date; all must fit a full half-hour inside 09:00–17:00."
      • addedOutput schema / properties / input / properties / people / items / properties / name / description
        Added value: +"Participant label used in the returned local-time display."
      • addedOutput schema / properties / input / properties / people / items / properties / name / examples
        Added value: +[
+  "Sam"
+]
      • changedOutput schema / properties / input / properties / people / items / properties / zone / description
        Previous value: -"An IANA time zone supported by Intl.DateTimeFormat, such as America/New_York."New value: +"IANA time zone supported by Intl.DateTimeFormat."
      • addedOutput schema / properties / input / properties / people / items / properties / zone / examples
        Added value: +[
+  "America/New_York",
+  "Asia/Kolkata"
+]
      • addedOutput schema / properties / method / description
        Added value: +"Calculation or ranking method applied to the inputs."
      • addedOutput schema / properties / overlapCount / description
        Added value: +"Number of candidate slots inside every participant’s workday."
      • addedOutput schema / properties / provenance / additionalProperties / description
        Added value: +"Unit or source detail for the named field."
      • addedOutput schema / properties / provenance / description
        Added value: +"Dated data sources or runtime time-zone information used for this result."
      • addedOutput schema / properties / rows / description
        Added value: +"All candidate half-hour starts on the first participant’s local date, in chronological order."
      • addedOutput schema / properties / rows / items / properties / inside / description
        Added value: +"Whether each participant’s full half-hour fits their 09:00–17:00 workday, in input order."
      • addedOutput schema / properties / rows / items / properties / labels / description
        Added value: +"Local start labels for participants in input order."
      • addedOutput schema / properties / rows / items / properties / score / description
        Added value: +"Sum of absolute hours from 13:00 at each participant’s slot midpoint; lower ranks first."
      • addedOutput schema / properties / rows / items / properties / startUtc / description
        Added value: +"Start instant in ISO 8601 UTC."
      • addedOutput schema / properties / tool / description
        Added value: +"Calculator identifier for this result."
      • addedOutput schema / properties / units / additionalProperties / description
        Added value: +"Unit or source detail for the named field."
      • addedOutput schema / properties / units / description
        Added value: +"Units for the numeric and time fields in this result."
    • Changedrecurring_schedule65 fields changed
      • changedInput schema / properties / startDate / description
        Previous value: -"Real date from 2000-01-01 to 2100-12-31."New value: +"Earliest date for the first occurrence of each task, from 2000-01-01 to 2100-12-31."
      • addedInput schema / properties / startDate / examples
        Added value: +[
+  "2026-10-05"
+]
      • addedInput schema / properties / startDate / maxLength
        Added value: +10
      • addedInput schema / properties / startDate / minLength
        Added value: +10
      • addedInput schema / properties / tasks / description
        Added value: +"Tasks to include in the estimate and calendar. [] returns zero hours and a calendar with no events."
      • addedInput schema / properties / tasks / items / properties / day / description
        Added value: +"Weekday for weekly/biweekly tasks. Required but ignored for monthly tasks."
      • addedInput schema / properties / tasks / items / properties / day / examples
        Added value: +[
+  "MO"
+]
      • addedInput schema / properties / tasks / items / properties / frequency / description
        Added value: +"Repeat every week, every two weeks from the first matching weekday, or every month."
      • addedInput schema / properties / tasks / items / properties / minutes / description
        Added value: +"Estimated minutes per run; used for event duration and monthly hours."
      • addedInput schema / properties / tasks / items / properties / minutes / examples
        Added value: +[
+  35
+]
      • addedInput schema / properties / tasks / items / properties / monthday / description
        Added value: +"Day of month for monthly tasks, limited to dates present in every month. Required but ignored for weekly/biweekly tasks."
      • addedInput schema / properties / tasks / items / properties / monthday / examples
        Added value: +[
+  1
+]
      • addedInput schema / properties / tasks / items / properties / owner / description
        Added value: +"Planning label: delegate to an operator, keep for yourself, or decide later. Included in the calendar note; does not assign or execute work."
      • addedInput schema / properties / tasks / items / properties / time / description
        Added value: +"24-hour HH:mm start time, floating in the importing calendar’s local time zone."
      • addedInput schema / properties / tasks / items / properties / time / examples
        Added value: +[
+  "09:00"
+]
      • addedInput schema / properties / tasks / items / properties / time / maxLength
        Added value: +5
      • addedInput schema / properties / tasks / items / properties / time / minLength
        Added value: +5
      • addedInput schema / properties / tasks / items / properties / title / description
        Added value: +"Task label used as the calendar event summary."
      • addedInput schema / properties / tasks / items / properties / title / examples
        Added value: +[
+  "Investor update"
+]
      • addedOutput schema / description
        Added value: +"Monthly effort estimate, normalized recurrence rules and an importable floating-time calendar."
      • addedOutput schema / properties / assumptions / description
        Added value: +"Limits and assumptions to retain when presenting the result."
      • addedOutput schema / properties / input / description
        Added value: +"Normalized inputs used for this calculation."
      • changedOutput schema / properties / input / properties / startDate / description
        Previous value: -"Real date from 2000-01-01 to 2100-12-31."New value: +"Earliest date for the first occurrence of each task, from 2000-01-01 to 2100-12-31."
      • addedOutput schema / properties / input / properties / startDate / examples
        Added value: +[
+  "2026-10-05"
+]
      • addedOutput schema / properties / input / properties / startDate / maxLength
        Added value: +10
      • addedOutput schema / properties / input / properties / startDate / minLength
        Added value: +10
      • addedOutput schema / properties / input / properties / tasks / description
        Added value: +"Tasks to include in the estimate and calendar. [] returns zero hours and a calendar with no events."
      • addedOutput schema / properties / input / properties / tasks / items / properties / day / description
        Added value: +"Weekday for weekly/biweekly tasks. Required but ignored for monthly tasks."
      • addedOutput schema / properties / input / properties / tasks / items / properties / day / examples
        Added value: +[
+  "MO"
+]
      • addedOutput schema / properties / input / properties / tasks / items / properties / frequency / description
        Added value: +"Repeat every week, every two weeks from the first matching weekday, or every month."
      • addedOutput schema / properties / input / properties / tasks / items / properties / minutes / description
        Added value: +"Estimated minutes per run; used for event duration and monthly hours."
      • addedOutput schema / properties / input / properties / tasks / items / properties / minutes / examples
        Added value: +[
+  35
+]
      • addedOutput schema / properties / input / properties / tasks / items / properties / monthday / description
        Added value: +"Day of month for monthly tasks, limited to dates present in every month. Required but ignored for weekly/biweekly tasks."
      • addedOutput schema / properties / input / properties / tasks / items / properties / monthday / examples
        Added value: +[
+  1
+]
      • addedOutput schema / properties / input / properties / tasks / items / properties / owner / description
        Added value: +"Planning label: delegate to an operator, keep for yourself, or decide later. Included in the calendar note; does not assign or execute work."
      • addedOutput schema / properties / input / properties / tasks / items / properties / time / description
        Added value: +"24-hour HH:mm start time, floating in the importing calendar’s local time zone."
      • addedOutput schema / properties / input / properties / tasks / items / properties / time / examples
        Added value: +[
+  "09:00"
+]
      • addedOutput schema / properties / input / properties / tasks / items / properties / time / maxLength
        Added value: +5
      • addedOutput schema / properties / input / properties / tasks / items / properties / time / minLength
        Added value: +5
      • addedOutput schema / properties / input / properties / tasks / items / properties / title / description
        Added value: +"Task label used as the calendar event summary."
      • addedOutput schema / properties / input / properties / tasks / items / properties / title / examples
        Added value: +[
+  "Investor update"
+]
      • addedOutput schema / properties / method / description
        Added value: +"Calculation or ranking method applied to the inputs."
      • addedOutput schema / properties / monthlyHours / description
        Added value: +"Estimated monthly hours using 52/12 weekly, 26/12 biweekly and one monthly run."
      • addedOutput schema / properties / provenance / additionalProperties / description
        Added value: +"Unit or source detail for the named field."
      • addedOutput schema / properties / provenance / description
        Added value: +"Dated data sources or runtime time-zone information used for this result."
      • addedOutput schema / properties / schedules / description
        Added value: +"Normalized tasks with their first occurrence and recurrence rule, in input order."
      • addedOutput schema / properties / schedules / items / properties / day / description
        Added value: +"Weekday for weekly/biweekly tasks. Required but ignored for monthly tasks."
      • addedOutput schema / properties / schedules / items / properties / day / examples
        Added value: +[
+  "MO"
+]
      • addedOutput schema / properties / schedules / items / properties / firstDate / description
        Added value: +"First occurrence on or after startDate."
      • addedOutput schema / properties / schedules / items / properties / frequency / description
        Added value: +"Repeat every week, every two weeks from the first matching weekday, or every month."
      • addedOutput schema / properties / schedules / items / properties / minutes / description
        Added value: +"Estimated minutes per run; used for event duration and monthly hours."
      • addedOutput schema / properties / schedules / items / properties / minutes / examples
        Added value: +[
+  35
+]
      • addedOutput schema / properties / schedules / items / properties / monthday / description
        Added value: +"Day of month for monthly tasks, limited to dates present in every month. Required but ignored for weekly/biweekly tasks."
      • addedOutput schema / properties / schedules / items / properties / monthday / examples
        Added value: +[
+  1
+]
      • addedOutput schema / properties / schedules / items / properties / owner / description
        Added value: +"Planning label: delegate to an operator, keep for yourself, or decide later. Included in the calendar note; does not assign or execute work."
      • addedOutput schema / properties / schedules / items / properties / recurrenceRule / description
        Added value: +"RFC 5545 RRULE matching the task frequency and day."
      • addedOutput schema / properties / schedules / items / properties / time / description
        Added value: +"24-hour HH:mm start time, floating in the importing calendar’s local time zone."
      • addedOutput schema / properties / schedules / items / properties / time / examples
        Added value: +[
+  "09:00"
+]
      • addedOutput schema / properties / schedules / items / properties / time / maxLength
        Added value: +5
      • addedOutput schema / properties / schedules / items / properties / time / minLength
        Added value: +5
      • addedOutput schema / properties / schedules / items / properties / title / description
        Added value: +"Task label used as the calendar event summary."
      • addedOutput schema / properties / schedules / items / properties / title / examples
        Added value: +[
+  "Investor update"
+]
      • addedOutput schema / properties / tool / description
        Added value: +"Calculator identifier for this result."
      • addedOutput schema / properties / units / additionalProperties / description
        Added value: +"Unit or source detail for the named field."
      • addedOutput schema / properties / units / description
        Added value: +"Units for the numeric and time fields in this result."
  2. 5 tool updatesv1.0.0
    • First observedai_api_cost
    • First observedai_subscription_stack_cost
    • First observedcron_next_runs
    • First observedmeeting_time_zones
    • First observedrecurring_schedule
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.7/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose, and the descriptions explicitly cross-reference siblings (e.g., ai_api_cost vs. ai_subscription_stack_cost, meeting_time_zones vs. recurring_schedule vs. cron_next_runs). There is no meaningful overlap that would cause misselection.

Naming Consistency5/5

All names use consistent snake_case noun phrases (ai_api_cost, meeting_time_zones, recurring_schedule, ai_subscription_stack_cost, cron_next_runs). No mixed conventions or vague verbs appear.

Tool Count5/5

Five tools is well within the ideal 3–15 range, and each tool earns its place with a distinct capability. The set is neither bloated nor too thin for a utility server.

Completeness4/5

The surface covers AI cost estimation (API and subscriptions) and scheduling utilities (meeting overlap, recurring task plans, cron preview). Minor gaps exist, such as no holiday lookup or general time-zone conversion, but core workflows are complete and agents can work around these.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Cron Parser API

    Br0ski777
    A
    license
    Not graded
    quality
    D
    maintenance
    Parse, validate, and explain cron expressions with pay-per-call via x402 (USDC on Base L2), returning next run times in any timezone.
    1
    MIT

  • leftbrain

    Lazy-Coder-03
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides exact, deterministic tools for math, dates, units, validation, and more to AI agents, returning precise answers with explicit assumptions and warnings instead of model guesses.
    MIT