Skip to main content
Glama

Agentry — The Trust Layer for the Agent Economy

by io.github.cthulhutoo

search_agents_api_agents_search_get

Search Agents

Search the Agentry AI agent directory by keyword.

Performs a full-text search across agent names, descriptions, key features, and integration lists. Returns matching agents ranked by relevance with trust scores, pricing, and capability metadata.

Responses:

200: Successful Response (Success Response) Content-Type: application/json

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoSearch keyword to match against agent name, description, features, and integrations. Examples: 'customer support', 'slack', 'code review', 'sales automation'.
limitNoMaximum number of search results to return. Range: 1-100.
offsetNoNumber of results to skip for pagination.
categoryNoOptionally narrow search results to a specific category (e.g. 'Sales & Outreach', 'Customer Support').

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds valuable context beyond the schema by explaining that the search is full-text across multiple fields and that results are ranked by relevance with trust scores, pricing, and capability metadata. This covers the core behavior and return content, though it does not mention pagination behavior or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded and relatively concise, with the first sentence defining the tool's purpose. However, it includes a redundant '### Responses' section that states 'Successful Response' and 'Content-Type' without useful information, which adds slight clutter. Overall, it is mostly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains what the tool returns (matching agents, ranking, trust scores, pricing, metadata) even though there is no output schema. It covers the search scope and output content sufficiently for a search operation. Pagination is left to the schema's limit/offset parameters, which is acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the schema descriptions already provide detailed parameter semantics including examples, ranges, and constraints. The tool description adds no additional parameter-specific meaning, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches the agent directory by keyword, specifies the exact fields searched (names, descriptions, features, integrations), and describes the output (ranked results with trust scores, pricing, capability metadata). This distinguishes it from sibling tools like list_agents, which likely returns all agents without keyword ranking.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies when to use this tool: when you need to find agents by keyword. However, it does not explicitly mention alternatives (e.g., list_agents for browsing all agents, or get_agent for fetching a single agent) or state when not to use it. This is clear context but lacks explicit differentiation guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Agentry — The Trust Layer for the Agent Economy toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.3/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, with descriptions that differentiate related operations like discovery vs. scanning or mint vs. melt quotes. A few pairs (e.g., list_agents vs. a2a_public_discovery, get_agent vs. discover_single_agent) could cause confusion, but the endpoint paths and descriptions mitigate this.

Naming Consistency5/5

All tool names follow a consistent pattern: a descriptive operation prefix followed by the full API path and HTTP method (e.g., list_agents_api_agents_get, create_melt_quote_api_payments_ecash_melt_quote_post). No mixed casing or inconsistent verb styles.

Tool Count2/5

With 36 tools, the server is overloaded. Even though it covers multiple domains (directory, trust, discovery, payments), the count exceeds the 25+ threshold and likely should be split into focused sub-servers. The tool set feels sprawling rather than well-scoped.

Completeness4/5

The core workflows for agent registration, search, trust, A2A discovery, scanning, and ecash payments are well-covered. Minor gaps exist, such as no update or delete agent operations and no way to modify agent details post-registration, but these are not critical dead-ends for the platform's purpose.

Resources