Skip to main content
Glama

Bench Agent Discovery

Server Details

Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.1/5 across 3 of 3 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool has a clearly distinct purpose: get_agent retrieves details of a specific agent, list_benchmarks returns benchmark contracts and submissions, and search_agents finds agents by various criteria. No overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (get_agent, list_benchmarks, search_agents) using snake_case, making the interface predictable.

Tool Count4/5

Three tools is slightly low but appropriate for a read-only discovery server, covering core operations (get, list, search). Could potentially benefit from an additional tool for benchmark details, but the count is reasonable.

Completeness4/5

The tool set covers the main discovery workflows: retrieving an agent, searching agents, and listing benchmarks. A minor gap is the lack of a dedicated tool to get detailed benchmark information, but agents can still work around this.

Available Tools

3 tools
get_agentGet a public agentA
Read-onlyIdempotent
Inspect

Get one public agent's recipe, public capability manifest, coarse invocation status, owner telemetry, and verified benchmark submissions.

ParametersJSON Schema
NameRequiredDescriptionDefault
handleYesBench handle in @owner/agent-slug form.
Behavior4/5

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context by enumerating the returned data fields (recipe, capability manifest, coarse invocation status, owner telemetry, verified benchmark submissions), which goes beyond annotations.

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

Conciseness5/5

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

The description is a single sentence that efficiently lists the returned data. No redundant words or filler. Perfectly concise for a simple GET endpoint.

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?

Given the tool has only one parameter and no output schema, the description provides a reasonable enumeration of response components. It lacks mention of error conditions or availability constraints, but for a read-only single-agent retrieval, it is largely complete.

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 description coverage is 100% (the only parameter 'handle' has a description: 'Bench handle in @owner/agent-slug form.'). The tool description does not add extra meaning beyond the schema; it only reiterates that the agent is public. Baseline 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 verb 'Get' and the resource 'one public agent', listing specific data components (recipe, capability manifest, invocation status, telemetry, benchmark submissions). This distinguishes it from sibling tools list_benchmarks and search_agents, which target different resources or operations.

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

Usage Guidelines2/5

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

The description does not provide explicit guidance on when to use this tool versus its siblings. There is no mention of when not to use it (e.g., for searching across agents) or alternatives. The context is implied but not spelled out.

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

list_benchmarksList verified benchmark contractsA
Read-onlyIdempotent
Inspect

List public, versioned benchmark contracts and only their trusted-runner-verified submissions.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Behavior4/5

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

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. Description adds that only 'public, versioned' and 'trusted-runner-verified submissions' are listed, offering valuable context beyond annotations.

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

Conciseness5/5

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

Single sentence with no wasted words. Includes all necessary qualifiers (public, versioned, verified).

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

Completeness5/5

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

For a parameterless list tool, description fully covers what is listed and the filtering criteria. No output schema is needed as the purpose is clear.

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

Parameters4/5

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

No parameters are needed, so baseline is 4. The description doesn't need to explain parameters, and it appropriately avoids doing so.

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?

Description clearly states 'List public, versioned benchmark contracts' with verb 'list' and specific resource. Specifies filtering to 'trusted-runner-verified submissions', distinguishing it from sibling tools about agents.

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

Usage Guidelines3/5

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

No explicit when-to-use or alternatives, but context suggests it's for listing benchmarks. The simplicity of the tool (no parameters) reduces the need for extensive guidance.

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

search_agentsSearch public AI agentsA
Read-onlyIdempotent
Inspect

Find listed public agents by task, capability, category, framework, model, verified evidence, or reuse configuration. Owner telemetry and controlled benchmark evidence are returned separately.

ParametersJSON Schema
NameRequiredDescriptionDefault
sortNoverified
limitNo
modelNo
queryNoTask or capability to search for, such as grounded research or code review.
licenseNoExact SPDX-style license id from the agent's manifest provenance, such as MIT or Apache-2.0.
categoryNo
reusableNoTrue returns agents whose owners configured an invocation policy and capability manifest.
verifiedNoTrue returns agents with at least one trusted-runner-verified benchmark submission.
frameworkNo
liveCallableNoTrue returns agents with a reusable invocation policy and an owner-verified, currently reachable endpoint.
maxP50LatencyMsNoUpper bound on the agent's observed p50 latency in milliseconds.
maxCostPerRunUsdNoUpper bound on lifetime total_cost_usd / total_runs, i.e. average observed cost per run.
Behavior4/5

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

Annotations provide readOnlyHint, idempotentHint, destructiveHint. The description adds value by stating that owner telemetry and controlled benchmark evidence are returned separately, and that only 'public' agents are searchable. 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.

Conciseness5/5

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

Two sentences, efficiently structured. First sentence enumerates searchable attributes, second clarifies return behavior. No unnecessary words. Front-loaded with key information.

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

Completeness3/5

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

With 12 parameters and no output schema, the description is brief. It does not explain sorting, default behavior (no filters), or pagination. The output format is hinted but not detailed. More could be said about the result structure given the complexity.

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 description coverage is 58%. The description lists types of search criteria but does not explain all parameters (e.g., sort, limit). It adds some semantic grouping but not per-parameter details. Baseline 3 because coverage is moderate and description partially compensates.

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 verb ('Find'), resource ('public agents'), and specifies multiple criteria (task, capability, category, framework, model, verified evidence, reuse configuration). It distinguishes from sibling tools: 'get_agent' retrieves a single agent, 'list_benchmarks' lists benchmarks.

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 implies usage when you want to search for agents by various filters. It mentions that owner telemetry and benchmark evidence are returned separately, giving context. However, it does not explicitly exclude cases when to use alternatives (e.g., if you know the agent ID, use get_agent). No explicit when-not guidance.

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

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.

Resources