Compare two canonical HMDA lender keys returned by search_lenders.
| Name | Required | Description | Default |
|---|---|---|---|
| top_n | No | ||
| lender_a | Yes | ||
| lender_b | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | ||
| meta | Yes |
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 the tool as read-only, idempotent, and non-destructive. The description adds no further behavioral context, such as what 'compare' means or what aspects are compared.
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 very concise (single sentence) but lacks structure and additional detail. It is efficient but under-specified for a tool with 3 parameters.
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?
Despite having an output schema and annotations, the description does not explain what the comparison entails (e.g., differences, similarities, metrics). The tool's purpose is clear, but the missing behavioral and parameter context leaves the agent underinformed.
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 0%, and the description fails to explain any parameters, including the optional 'top_n' which controls result count. The description does not compensate for the missing schema details.
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 verb 'compare' and the resource 'canonical HMDA lender keys', and references the sibling tool 'search_lenders', distinguishing it from other tools.
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 description implies usage after search_lenders, but does not explicitly state when to use this tool versus alternatives like get_lender_profile or get_market_snapshot.
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.
Most tools target clearly distinct data domains: lender search/profile/compare cluster around HMDA lender analytics, while market snapshot, loan performance, servicer analytics, and SEC filing tools are separate. The only minor ambiguity is between get_lender_profile, compare_lenders, and search_lenders which all deal with lender keys, though their intents (search vs. profile vs. comparison) are distinct.
Tools follow a consistent get_/search_/compare_ verb pattern with clear noun targets (lenders, market_snapshot, loan_performance, sec_filing). The one deviation is that search_lenders, search_sec_filings, and compare_lenders use non-get verbs while the rest use get_, but this is a sensible pattern matching read vs. search semantics.
At 9 tools, this is well within the ideal 3-15 range and each tool appears to represent a meaningful consumer capability for a mortgage analytics domain. The count feels appropriately scoped without redundancy or bloat.
The surface covers market data, SEC filings, lender profiles, loan performance, and servicer analytics, but there are notable gaps: there's no mutation capability (all read-oriented), no way to combine or join across these domains, and no search tool for loan performance or market data topics - those are limited to pre-bounded topics. Some domains feel like they have single query points rather than full browsing coverage.
