seodraft

Complete onboarding

complete_onboarding

Idempotent

Finishes setup once the profile has business name, description, audience, site URL and language, and 12-15 search phrases are stored with add_topics. Deterministic: no model call, and DataForSEO is optional. With credentials connected it measures the topics no paid call has covered in one batch (~USD 0.115), then builds a citability brief for the best-evidenced topic (one SERP, ~USD 0.004); mode comes back validated. Without credentials it spends nothing and returns a first brief with mode: preview, built from the topic the founder named, with every market signal unmeasured (dataConnected: false is not an error; credentials are a persistent secret collected in the web app). Does not use the brand or competitor names as seeds. Reports the data state in one vocabulary: observed (the provider returned a number, 0 included), unavailable (asked, nothing reported), unmeasured (never asked). measurement.attempted / answered / unanswered names the topics DataForSEO did or did not answer for, alongside measurement.reportedVolume and measurement.aiVolumeSignal. signals covers the whole bank: queriesChecked, reportedVolume (0 counts), aiVolumeSignal (above zero only), aiOverviewFound, relatedQuestions, and noVolumeReported (true when no topic carries a provider-reported volume, which is normal for long-tail questions). firstBriefEvidence names what the pick rested on: volumeStatus, aiVolumeStatus, aiOverview (found | absent | unmeasured), relatedQuestions, citedDomains, ownSite, serpObserved, and rule (volume-signal | serp-evidence | unranked). firstBriefObserved is the raw SERP verbatim (AI Overview state, cited domains, People Also Ask, result titles, builtAt) or null when none was read. analysisRequest names the tool (submit_topic_analysis), the topic, and the exact strings admissible as evidence for the gaps, angles and intent-grouped questions it asks for. firstBriefAnalysis is what is already stored, if anything. A partial measurement still returns status ready. A ready result activates the workspace (idempotent); activationUrl is the app root.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`workspaceId`	No	The workspace this call acts on, as listed by list_workspaces. Left out, the call uses the workspace the account is in right now.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 2, 2026

addedInput schema / properties / workspaceId

Added value: +{
+  "description": "The workspace this call acts on, as listed by list_workspaces. Left out, the call uses the workspace the account is in right now.",
+  "type": "string"
+}

First observedSep 27, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Far exceeds the annotations, which only declare non-read-only, open-world, idempotent, non-destructive. The description adds determinism ('no model call'), cost estimates (~USD 0.115 / ~USD 0.004), the credentials-optional branch, the validated vs preview mode semantics, and the explicit caveat that dataConnected:false is not an error, and that a partial measurement still returns ready.

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 opening sentence is well front-loaded and states purpose, precondition and determinism. However the remainder is an undifferentiated block that mixes cost, auth branching, response vocabulary and field-by-field return documentation into dense prose, making it hard to scan; some of the measurement/signal field detail could be tightened.

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?

With no output schema and a complex, branching operation, the description carries the full burden and largely succeeds: it documents mode values, dataConnected semantics, the observed/unavailable/unmeasured vocabulary, the signals and firstBriefEvidence fields, and activationUrl. It is close to complete for an agent to interpret the result, with only minor ambiguity remaining.

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?

With a single optional parameter and a 100% schema description coverage, the schema already defines workspaceId's meaning and its runtime fallback. The description adds no further parameter-level guidance, so the baseline 3 applies.

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 action (finishing setup/onboarding) and its completion conditions: profile fields populated and 12-15 search phrases stored via add_topics. It names related siblings (add_topics, submit_topic_analysis) so the agent can locate it in the workflow, though it never says explicitly how it differs from the other research/planning 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?

Gives a concrete precondition for calling it (profile complete + topics stored) and clearly partitions behavior by credential state (with credentials: measure + brief, mode validated; without: preview, no spend). It stops short of naming alternatives to use instead if the precondition is not yet met, so the agent must infer that gap.

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

All seodraft tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?