site_audit_getPoll an audit started with site_audit_start (free to read). When finished, returns the issue list grouped by severity with affected URLs — work through it top-down and re-run after fixes.
| Name | Required | Description | Default |
|---|---|---|---|
| audit_id | Yes | Audit id from site_audit_start |
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?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral context: it's 'free to read', it's a polling operation, and it returns the issue list grouped by severity with affected URLs. This goes beyond the annotations and helps the agent understand the tool's behavior.
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 a single, dense sentence that conveys purpose, usage, output, and workflow with no redundancy. It is front-loaded with the key verb and resource.
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 simple 1-parameter read tool with good annotations, the description fully explains when to use it, what it returns, and how to act on the results. No output schema exists, so describing the return format is valuable and done.
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 has 100% coverage with audit_id described as 'Audit id from site_audit_start'. The description does not add further parameter detail, but the schema is sufficient. Baseline 3 applies since the schema handles the parameter semantics.
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 function: polling an audit started with site_audit_start and returning the issue list. It names the specific resource (site audit) and distinguishes itself from sibling site_audit_start by explicitly referencing it as the start operation.
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 ties usage to site_audit_start ('Poll an audit started with site_audit_start'), indicates when to use it ('When finished'), and provides a workflow ('work through it top-down and re-run after fixes'). This gives clear context and alternatives.
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.