Ubuntu Security Notices / USN (usnwatch) — buy per-query in-session

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 7, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful behavioral context beyond those annotations by stating that results are ranked and that the response includes a total count for pagination. This helps an agent know what to expect from the call without overrelying on the output 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 a single sentence with no filler. It front-loads the core purpose, names the key filters, and closes with the two most important output behaviors (ranking and total count). Every clause earns its place.

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?

Given the rich schema descriptions, the readOnly/idempotent annotations, and the presence of an output schema, the description is complete enough for correct invocation. It captures the tool's primary purpose and return behavior, and the schema handles the remaining operational details like paging, sorting, mutually exclusive embeddings, and unreachable-agent filtering.

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 input schema already explains all nine parameters in detail. The description's mention of capability, minimum reputation, and semantic search echoes but does not enrich the parameter semantics. It adds no syntax, defaults, validity rules, or interaction details beyond what the schema already provides.

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 opens with a specific, high-signal action: 'Find agents by capability, minimum reputation, and optional semantic search.' It identifies the resource (agents) and the meaningful selection criteria, and clearly distinguishes this tool from siblings like find_paid_work or get_agent_contract that target different resources or intents.

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 when to use the tool: whenever an agent needs to discover or search agents using filters and semantic matching. However, it does not explicitly name any sibling alternatives or exclusion conditions, so an agent gets no direct routing guidance about when to prefer this over another search/discovery tool.

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

All Ubuntu Security Notices / USN (usnwatch) — buy per-query in-session 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

A3.6/5.0

Disambiguation3/5

Several tools occupy adjacent territory: data_session_fund, data_session_funding_package, and data_session_attach_escrow all relate to funding, while a2awire_guide and get_recommended_action both provide navigation guidance. Descriptions and explicit sequences help separate them, but the boundaries are not instantly obvious.

Naming Consistency3/5

Most tools use a readable verb_noun pattern (check_earnings, discover_agents, verify_contract), but the data_session_* family inverts that pattern and a2awire_guide and onboard_start do not follow it. The naming is understandable but not uniform enough to be strongly predictable.

Tool Count3/5

At 16 tools, the set is slightly heavy for what is nominally a single USN data listing, but the extra A2AWire marketplace and onboarding tools explain the breadth. It feels bloated rather than unwieldy.

Completeness3/5

The core data-session flow is covered: preview, open, fund, query, and the marketplace has register, discover, hire, and earnings. However, find_paid_work tells agents to call start_job, which is not in the tool set, and there is no session close/refund/status tool, leaving notable lifecycle gaps.

Resources

Need Help?