RiverWatch: USGS river levels & stream-flow gauges — per query

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

A4.2/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, and non-destructive behavior, so the description does not need to repeat those. It adds useful behavioral details: results are ranked and a total count is returned for pagination, and semantic search is optional. It aligns with the annotations and does not claim or imply side effects.

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 long and front-loads the core purpose followed by the output characteristic. Every word contributes: 'Find agents', the filter dimensions, optional semantic search, and pagination-relevant total count. No fluff or redundancy.

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 definition is complete enough because an output schema exists and all parameters are thoroughly documented in the schema. The description captures the primary use case and the key output detail needed for pagination. It does not mention verified or include_unreachable filters, but those are fully specified in the schema, so the high-level description remains adequate.

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 all 9 parameters already have meaningful descriptions and constraints. The tool description adds a high-level summary of capability, min_reputation, and semantic query filters, but does not provide deeper semantics than the schema. Baseline 3 is appropriate given full schema coverage.

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 uses a specific verb-resource pair, 'Find agents', and enumerates the key filtering dimensions: capability, minimum reputation, and optional semantic search. It also states the output nature (ranked matches with total count). This clearly distinguishes it from sibling tools like hire_and_execute or find_paid_work, which cover different workflow steps.

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 gives clear context: use this tool when you need to discover or search for agents by filters. It does not explicitly exclude alternative tools, but no sibling appears to offer the same agent-discovery function, so explicit alternatives are not necessary. A small deduction for not stating 'when not to use'.

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

All RiverWatch: USGS river levels & stream-flow gauges — per query 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

B3.3/5.0

Disambiguation2/5

Several tools occupy overlapping roles: data_session_fund, data_session_funding_package, and data_session_attach_escrow all describe funding or payment for a data session, while a2awire_guide, get_recommended_action, and onboard_start all point toward 'what to do next.' An agent could easily misroute payment or onboarding intent.

Naming Consistency4/5

Most names follow a snake_case verb_noun pattern like data_session_open, find_paid_work, and verify_contract. The pattern is weakened by data_session_funding_package and a2awire_guide, which are noun-style, and by the confusingly similar data_session_fund vs. data_session_funding_package.

Tool Count2/5

16 tools is not inherently too many, but almost all of them belong to A2AWire marketplace/onboarding/payment infrastructure. Only data_preview and data_session_query actually relate to river data, so the count is poorly matched to the stated RiverWatch purpose.

Completeness2/5

The river-data surface is extremely thin: a preview and a generic paid query, with no station list, gauge search, metadata, units, or historical access. The session lifecycle also lacks explicit close or refund flows, leaving significant gaps for a realistic river-data use case.

Resources

Need Help?