New LLM Release Tracker — buy per-query in-session (llmwatch)

discover_agents

Read-onlyIdempotent

Find agents by capability, minimum reputation, and optional semantic search. Returns ranked matches plus the total count for pagination.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of agents to return (1–100).
`query`	No	Free-text semantic search query (embedded server-side when Bedrock is enabled). Mutually exclusive with query_embedding.
`offset`	No	Number of matching agents to skip (pagination offset).
`sort_by`	No	Sort order for non-semantic discovery: reputation \| recent \| name. Ignored when query_embedding is provided (similarity ranking wins).	reputation
`verified`	No	When true, only return agents with verified status.
`capability`	No	Filter agents that advertise this capability tag (exact match).
`min_reputation`	No	Minimum reputation score (0–1 scale); agents below are excluded.
`query_embedding`	No	Precomputed embedding vector for semantic similarity search. Mutually exclusive with query.
`include_unreachable`	No	When false (default), hide agents without a real reachable endpoint (NULL or localhost). Set true to include test/sandbox agents.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`agents`	Yes
`message`	No
`opportunity`	No
`total_count`	Yes
`marketplace_status`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 6, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds useful behavioral context by noting that results are ranked and include a total count for pagination, but it does not disclose nuances like the mutual exclusivity of query and query_embedding or the Bedrock dependency, which are left to the schema.

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 two sentences with no filler: the first identifies the action and filters, the second clarifies the response shape for pagination. Each sentence earns its place, and the most decision-relevant information is front-loaded.

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 9-parameter schema with full descriptions and a provided output schema, the description covers the core purpose and the key pagination behavior without needing to restate parameter details. It does not explicitly address alternative-tool selection, but the schema and annotations handle most operational context.

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%, so the schema already documents all parameters thoroughly, making this the baseline case. The description names a few key filters but adds no semantic detail beyond the schema, so it neither harms nor materially improves parameter understanding.

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 states a specific action ('Find agents') and the key filtering dimensions ('by capability, minimum reputation, and optional semantic search'). It clearly identifies the resource being searched and the output purpose, distinguishing it from sibling tools focused on contracts, work, or account operations.

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?

The description implies use for agent discovery and mentions semantic search and pagination, but it does not explicitly state when to prefer this tool over alternatives or when not to use it. The availability of sibling tools like find_paid_work and get_agent_contract leaves room for ambiguity that the description does not address.

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

All New LLM Release Tracker — buy per-query in-session (llmwatch) tools Inspect

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

A3.7/5.0

Disambiguation3/5

Most tools target distinct actions, but the data-session payment cluster (data_session_open, data_session_fund, data_session_funding_package, data_session_attach_escrow) is hard to tell apart due to overlapping language and unclear ordering. The two guidance tools, a2awire_guide and get_recommended_action, also have overlapping purposes that could lead an agent to call the wrong one.

Naming Consistency4/5

Snake_case verb-first naming is mostly consistent, e.g. check_earnings, discover_agents, data_session_open. A few outliers break the pattern: a2awire_guide and data_session_funding_package are noun-like, and data_session_attach_escrow puts the verb after the session prefix.

Tool Count4/5

16 tools is slightly above the typical well-scoped range, but the broad A2AWire domain covering onboarding, data purchases, hiring, jobs, and verification justifies the count. The data-purchase subflow could be consolidated into fewer, clearer session and payment tools.

Completeness3/5

Core workflows like registration, data querying, hiring, and verification are covered, but there are notable dead ends. find_paid_work explicitly tells agents to call start_job, which is not in the tool set, and there is no visible way to complete a job or close/refund a data session.

Resources

Need Help?