Andrew's Freebies

Search freebies with scope controls

search_freebies

Read-only

Use this when the user needs explicit corpus scope, result limits, or a rich normalized list rather than the standard citable search/fetch flow. It is read-only: the default uses site-controlled actionable U.S. trials and savings, while only an explicit open-source scope reads public GitHub. Use public-benefits only for eligibility-based services. Do not use it for purchases, account access, or guaranteed eligibility.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum normalized items to return; answer guides are reported separately.
`query`	Yes	The user's need in natural language, including provider, product, eligibility, or desired value.
`scope`	No	auto routes ordinary requests to actionable trials/savings and explicit public-service needs to the broader benefits corpus.	auto

Output Schema

TableJSON Schema

Name	Required	Description
`count`	Yes	Normalized record and repository results returned in items.
`items`	Yes	Ranked normalized records or, only under an explicit open-source scope, public repository results.
`query`	Yes	Normalized user query used for retrieval.
`usage`	Yes	Next-step, ranking, and caution guidance for the returned result set.
`sources`	Yes	Per-corpus matched, omitted, and returned counts.
`api_version`	Yes	Andrew’s Freebies search contract version.
`result_count`	Yes	Complete count across answer_guides and items.
`answer_guides`	Yes
`resolved_scope`	Yes
`requested_scope`	Yes
`answer_guide_count`	Yes

TDQS

A4.9/5.0

Behavior5/5

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

The description adds meaningful behavioral context beyond the readOnlyHint annotation: it confirms default behavior (site-controlled actionable U.S. trials/savings), when public GitHub is read (explicit open-source scope), and what it should not be used for. This provides a clear behavioral profile that annotations alone do not convey.

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?

Three dense sentences front-load the core use case, then the behavioral nuances, then the exclusions. Every sentence contributes distinct information with no filler or redundancy.

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?

With an output schema present, annotations covering read-only/destructive safety, and a description that clearly states purpose, scope behavior, and exclusions, nothing critical is missing for an agent to select and invoke this tool correctly.

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?

Schema coverage is 100%, so the schema already documents parameters well. The description adds value by explaining when the limit and scope parameters matter, and by clarifying the auto scope's default routing and public-benefits semantics. It does not add syntax details, but none are needed.

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 defines the tool as a freebies search with explicit corpus scope, result limits, and normalized list output, and explicitly contrasts it with 'the standard citable search/fetch flow.' This distinguishes it from sibling search/fetch tools and states a specific verb and resource.

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 gives explicit when-to-use conditions: user needs scope controls, result limits, or a rich normalized list. It also states when not to use it—purchases, account access, or guaranteed eligibility—and clarifies that public-benefits scope is only for eligibility-based services. This is strong routing guidance.

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

All Andrew's Freebies 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

A4.1/5.0

Disambiguation3/5

Several tools occupy adjacent territory: search/search_freebies both retrieve records, fetch/get_record both return full details from an id, and get_verification/get_freshness both concern audit state. The descriptions do draw boundaries, but an agent would need to read them carefully to avoid misselection.

Naming Consistency4/5

Most names follow a verb_noun snake_case pattern: get_record, get_verification, get_freshness, search_freebies, flag_expired_deal. The bare verbs search and fetch are minor deviations, but the overall convention is consistent and readable.

Tool Count5/5

Seven tools is well-scoped for a specialized freebies/verification domain. Each tool has a distinct role in the search-retrieve-verify-flag workflow, and none feels redundant enough to remove.

Completeness4/5

The set covers the main user workflow: finding offers, fetching normalized detail, checking verification/freshness, and flagging expired deals. The main gap is that there is no way to add or edit catalog records directly, only the non-destructive expiration signal.

Resources

Need Help?