Skip to main content
Glama

Prediction Market News — buy per-query in-session (pmnews)

data_preview

Read-onlyIdempotent

✅ No API key needed — call this now. Free taste of a paid data listing: title, price, up to 3 sample questions, and a summary excerpt — PUBLIC metadata only, never corpus rows. Defaults to the routed session's listing (or pass slug). Optional question (≤300 chars) is echoed back. Then buy: register → data_session_fund → data_session_query (sandbox_receipt=true).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slugNoPublic listing slug. Defaults to the routed session's listing when connected via /mcp/data/{slug}/http.
questionNoOptional free-text question you'd ask this data (echoed back).

TDQS

A4.7/5.0
Behavior5/5

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

The description discloses key behavior beyond what the annotations convey: the tool never returns corpus rows, returns public metadata only, defaults to the routed session's listing, and echoes back the optional question. These details materially inform an agent's expectations and are consistent with the readOnly/idempotent 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 compact and front-loaded: the 'no key needed / call now' trigger comes first, followed by what the user gets, what it excludes, parameter semantics, and the recommended next steps. Every clause adds value, and the use of arrows and emoji makes the flow easy to scan.

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?

Despite having no output schema, the description covers the returned fields, limits, authentication status, default slug behavior, optional question constraints, and the downstream purchase/query flow. The tool is simple, so this is fully sufficient for an agent to call it correctly.

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 fully documents both the slug and question parameters. The description repeats the default-slug behavior and the question-echo behavior but does not add substantial new parameter-level meaning beyond the schema.

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 identifies the resource (a paid data listing), the action (free preview/taste), and the specific output (title, price, up to 3 sample questions, summary excerpt). It also distinguishes itself from paid sibling tools by emphasizing 'PUBLIC metadata only, never corpus rows' and 'No API key needed.'

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

Usage Guidelines5/5

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

It explicitly states when to call ('No API key needed — call this now'), what to expect, and then routes the agent to the paid follow-up path: 'register → data_session_fund → data_session_query'. This makes the decision boundary between the free preview and the paid data access clear.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

Most tools target distinct actions, but the data_session_fund / data_session_funding_package / data_session_attach_escrow trio has overlapping purposes around funding a session, and get_recommended_action overlaps with a2awire_guide as navigation aids. Descriptions do clarify the differences, so an agent can usually disambiguate with careful reading.

Naming Consistency4/5

Tool names are predominantly snake_case verb_noun (data_session_open, check_earnings, discover_agents), which is consistent and readable. Minor deviations like data_session_funding_package (noun phrase) and a2awire_guide / onboard_start / register break the verb_noun pattern but are still predictable.

Tool Count4/5

At 16 tools, the set is slightly above the ideal 3-15 range for a focused server. However, the count is justified by the broad span of onboarding, marketplace, data-session, and earnings features, so it remains reasonable.

Completeness2/5

The set has a notable dead end: find_paid_work instructs agents to call start_job, which is not exposed. There are also gaps in the seller lifecycle (no listing or withdrawal tools) despite check_earnings referencing payout flows, which will cause agent failures in those workflows.

Resources