agency_statusFor a registered agency: its states, rail, terms, founding period, queued and delivered counts, credit balance, and whether the licence was verified. Requires the buyer key issued at confirmation.
| Name | Required | Description | Default |
|---|---|---|---|
| buyer_key | Yes | Issued to the licensed contact at confirmation |
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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds meaningful context beyond that: the data scope (counts, credit balance, verification flag) and the authentication need (buyer key issued at confirmation). 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 return-data list is front-loaded and the credential requirement is appended. Every phrase carries information, making this appropriately dense without being bloated.
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 one-parameter, read-only status tool with no output schema, the description supplies the return contract by enumerating the fields and stating the required credential. It does not cover error behavior for invalid or missing keys, but annotations mitigate that gap for a simple closed-world read.
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 100%, with buyer_key already documented as 'Issued to the licensed contact at confirmation.' The description essentially repeats that provenance without adding new format, constraints, or behavioral details, so the baseline of 3 applies.
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 names the resource (a registered agency) and enumerates the exact status fields returned: states, rail, terms, founding period, queued/delivered counts, credit balance, and licence verification. The retrieving verb is implied rather than stated, and it distinguishes well from siblings like register_agency and check_eligibility by scope, though not explicitly.
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?
The phrase 'For a registered agency' and the requirement of the buyer key provide clear context for when to call this tool. However, it never states when not to use it or explicitly routes to alternatives such as register_agency for creation or check_eligibility for pre-registration decisions; the guidance remains implied.
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 maps to a distinct step or resource: eligibility pre-check, quotes, consent/contact, agency registration, agency status, lead queue, market data, and data-use terms. Even the two quote-related tools are clearly sequenced with check_eligibility described as 'call this first'.
Five tools use a clear verb_noun pattern (check_eligibility, get_quotes, pull_requests, register_agency, request_agent_contact), but three are bare noun phrases (agency_status, data_use_terms, market_data). All names are readable and consistently snake_case, but the verb-led convention is not uniform.
Eight tools cover the main stages of an insurance marketplace: eligibility, quotes, consumer consent, agency onboarding, lead delivery, market data, and terms. The count is well-scoped and each tool earns its place.
The core consumer journey (eligibility → quotes → consented agent contact → lead delivery) and agency workflow (register → status → pull requests) are well covered, along with market data and terms. Minor gaps exist, such as no explicit update/removal for agency registration and consent revocation only mentioned as POST /forget rather than a tool.