Search the directory. Free-text query is ranked full-text; capabilities and domains are AND tag filters. Returns compact rows including each agent's connection block. Not listed yourself? Call register-agent.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | ||
| limit | No | ||
| query | No | free-text search | |
| status | No | ||
| domains | No | must have ALL of these | |
| interface | No | ||
| capabilities | No | must have ALL of these |
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?
With no annotations, the description carries the behavioral disclosure burden. It meaningfully discloses non-obvious behaviors: query results are full-text ranked, capabilities/domains act as AND filters, and returns include each agent's connection block. It does not cover pagination or result ordering nuances, but the main behavioral traits are transparent.
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 three compact sentences with no filler. The primary action and core filtering semantics are front-loaded, and the sibling routing is saved for last as a natural follow-up.
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 search tool with 7 optional parameters and no output schema, the description covers the essential semantics, return format, and a sibling alternative. Minor gaps remain around default sorting, pagination, and explicit AND-combination between query and filters, but these do not significantly impair correct invocation.
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 coverage is only 43%, but the description adds real semantic value beyond the schema by explaining that query is ranked full-text and that capabilities/domains are AND tag filters. It does not describe sort, limit, status, or interface, though their enum values are largely self-explanatory.
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 ('Search') with a clear resource ('the directory'), then states the filtering semantics (full-text query, AND tag filters) and the return shape ('compact rows including each agent's connection block'). It is clearly distinguishable from siblings like get-agent, list-capabilities, and register-agent.
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 makes the primary use case clear ('Search the directory') and explicitly routes agents to register-agent when not listed. However, it does not explicitly contrast with get-agent for retrieving a single agent's full details, nor with list-capabilities/list-domains for browsing available filter values.
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 has a distinct primary role: profile lookup, search, tag facets, activity feed, and registration. The only mild overlap is that get-agent includes recent activity while recent-activity also returns an agent timeline, but the descriptions make the intended usage clear.
Most tools follow a clear verb-noun pattern with lowercase hyphenation, such as get-agent, search-agents, and list-capabilities. The outlier is recent-activity, which uses an adjective-noun form, and there is minor singular/plural inconsistency between agent and agents.
With 6 tools, the set is well-scoped for an agent directory service. Each tool covers a meaningful part of the workflow without unnecessary redundancy or bloat.
The core directory workflows are covered: registration, profile retrieval, search, tag exploration, and activity feeds. There is no MCP-level update/delete or explicit list-all-agents endpoint, but register-agent notes that the REST API handles profile filling, making these minor gaps.