start_traceRun this when search_reports finds nothing (or the user wants fresh data) for "how did X grow?". Rebuilds the growth story from 12 public sources in 60-90s. Costs credits from the Tracetify balance; returns an existing cached report free instead when one is fresh. Poll with get_trace.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Domain to trace, e.g. weshop.ai | |
| refresh | No | Force a fresh run even if a cached report exists |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses behavioral traits beyond annotations: it incurs credits, takes 60-90 seconds, and may return a cached report for free if fresh. This adds context about side effects and efficiency, and does not contradict the annotations (readOnlyHint=false, destructiveHint=false).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the key trigger condition, and includes essential details (sources, time, cost, caching, polling) with no fluff. Every sentence serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that initiates a long-running, cost-incurring process, the description covers when to use it, what it does, how long it takes, cost implications, caching behavior, and how to retrieve results (via get_trace). This is sufficient for an agent to use it appropriately without an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters (url and refresh) are documented. The description adds value by explaining the caching behavior and cost implications, which indirectly clarifies the refresh parameter's effect (forcing a fresh run vs. potentially using a cached report for free). This is a slight enhancement over the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to start tracing how a product grew by rebuilding the growth story from 12 public sources. It distinguishes itself from search_reports by specifying it should be used when search_reports finds nothing or fresh data is needed, and from get_trace by indicating that get_trace is for polling results.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly provides usage context: 'Run this when search_reports finds nothing (or the user wants fresh data) for "how did X grow?"'. It also gives guidance on cost and caching behavior, and instructs to poll with get_trace, making the tool selection and follow-up steps clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource and action: backlink_directories vs research_backlinks differ (directories vs actual backlinks), gsc_* tools cover different views of own data (overview/pages/queries), research_* tools each address a separate question (competitors, domain overview, AI mentions, backlinks), and the trace/audit/report lifecycle tools have clear roles (start, poll, read, unlock). No two tools appear to do the same thing.
There is a clear pattern: verb_noun for actions (get_trace, read_report, start_trace, unlock_report, search_reports), research_* prefix for external lookups, gsc_* prefix for own Search Console data, and site_audit_* for audits. Minor inconsistency: backlink_directories doesn't follow the verb_noun style (no verb), but overall the naming is predictable and grouped logically.
At 15 tools, this is at the upper end of the well-scoped range (3-15). Each tool serves a distinct function within the SEO/growth analysis domain, so the count feels justified rather than bloated. However, it's slightly heavy, which is why it misses a 5.
The tool surface covers the full lifecycle of growth reports (search, read, start trace, poll, unlock), ownsite GSC data (overview, pages, queries), competitor research (domain, backlinks, brand, competitors), and site audits (start/get). Minor gaps include no way to delete or manage reports beyond reading, and no direct keyword research beyond GSC queries, but the core workflows are complete.