check_eligibilityCheck whether we can return quotes for a state before any personal details are collected. Call this first. Returns the states we are licensed in, what we can do in each, and how many licensed agents can take a request there.
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | Two-letter US state code, e.g. NV | |
| product | Yes | auto |
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, idempotentHint, and destructiveHint, so the description doesn't need to restate safety. It adds useful return-value context (licensed states, capabilities, agent counts) but does not disclose behaviors beyond that. No contradiction with annotations.
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?
Two sentences with zero filler. The action and 'call this first' directive lead, followed by a compact summary of return contents. Every sentence contributes.
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?
The description covers purpose, ordering, and broad return contents, but leaves the effect of the optional state parameter ambiguous (does it filter to one state or return all?). The product parameter is also unexplained outside the schema. For a simple read-only tool, these are moderate gaps.
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 description coverage is only 50%: state is documented but product is not. The tool description mentions 'state' but doesn't explain how the optional state filters results or what the product parameter means. It adds little semantic value beyond the schema, and with low coverage the description should compensate but doesn't.
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 uses a specific verb ('check') with a clear resource ('whether we can return quotes for a state') and a timing qualifier ('before any personal details are collected'). It distinguishes itself from get_quotes by being a pre-check and outlines the output content (licensed states, capabilities, agent counts).
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?
'Call this first' is an explicit ordering instruction that tells the agent when to invoke this tool. It doesn't name alternative tools or explain when not to use it, so it falls short of full routing guidance, but the first-step directive is clear and actionable.
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 clearly distinct function: eligibility checking, quoting, agent contact, agency registration/status/queue, data terms, and market data. The only adjacent pair, agency_status and pull_requests, is cleanly separated by status versus queue draining.
Five names use an imperative verb_noun pattern (check_eligibility, get_quotes, register_agency, pull_requests, request_agent_contact), while agency_status, data_use_terms, and market_data are resource-style names. All are lowercase underscore names and still readable, so this is a minor deviation rather than a chaotic mix.
Eight tools is well scoped for a platform covering eligibility, quotes, consumer contact, agency onboarding/status/queue, data terms, and market data. Each tool has a distinct job and none feels redundant.
The core journey is covered end to end: check eligibility, get quotes, request agent contact, register an agency, check status, and pull records. Minor gaps exist around agency profile updates/removal and exposing a revoke/forget action as a first-class tool, but agents can complete the main workflows without dead ends.