search_businessesFind tracked companies by name, metropolitan area, category, or minimum score.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| metro | No | ||
| query | No | Part of a company name | |
| category | No | ||
| min_score | No | ||
| verified_only | No | Only companies matched to a state entity record |
| Name | Required | Description | Default |
|---|---|---|---|
| total | Yes | ||
| results | Yes | ||
| provenance | 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 readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is clear. The description adds the scope of 'tracked companies' and the available filter dimensions, but does not disclose behavior such as result limits, pagination, or how verified_only affects results. With annotations covering safety, the added behavioral context is modest.
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 sentence that is front-loaded with the action ('Find tracked companies') and immediately lists the key filter dimensions. There is no redundant wording or filler.
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?
Given that the tool has an output schema, clear annotations, and a relatively straightforward search purpose, the description is mostly sufficient. It would benefit from mentioning that all filters are optional or combinable, and the limit parameter is not referenced, but the schema covers those details. Overall it is complete enough for a search tool.
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 33%, with query and verified_only described in the schema. The description helps by mapping natural language filters (name, metropolitan area, category, minimum score) to parameters, but it does not explain limit behavior or further clarify min_score semantics. It partially compensates for low schema coverage but not fully.
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 finds tracked companies by name, metro, category, or minimum score, using a specific verb and resource. It distinguishes this search tool from sibling tools like get_business_profile or compare_businesses by emphasizing criteria-based lookup.
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 when to use the tool by listing search criteria, but it does not explicitly mention alternatives or exclusions. For example, it does not say to use compare_businesses for comparisons or list_categories for category metadata, leaving usage guidance only 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 serves a clearly distinct purpose: comparing, profiling, explaining methodology, listing rankings, showing score breakdowns, listing categories and metros, and searching. There is minimal overlap; even get_business_profile vs get_score_breakdown differ in scope (full profile vs specific score).
All tool names follow a consistent verb_noun snake_case pattern using verbs like get, list, search, and compare. The objects are specific and match the action, making the naming predictable and readable.
With 8 tools, the set is well-scoped for a rankings-focused server. Each tool earns its place, covering navigation, retrieval, comparison, and methodology without unnecessary redundancy.
The server provides a complete read-only surface for the rankings domain: category and metro discovery, ranked lists, individual score breakdowns, comprehensive company profiles, comparison, search, and methodology. No obvious gaps exist for the stated purpose.