Fillin

fillin_answer

Read-onlyIdempotent

Synthesized post-cutoff answer with inline citations.

Use this when your model is small / cheap / weaker at tool-result
synthesis (Llama, Gemini Flash, Mistral, Nemotron, Qwen). Fillin runs
a server-side LLM pass over the retrieved post-cutoff documents and
returns a 150-250 word answer with [title](url) citations already
embedded — you can quote it directly.

Premium models (Opus, Sonnet, GPT-4o) usually get better results from
`fillin_query` and synthesizing themselves, but this tool works for
any caller. Costs more than fillin_query because of the synthesis pass.

Returns:
    A dict with:
      - answer: the synthesized paragraph (str | None)
      - citations: list of {title, url} extracted from the answer
      - corpus_match: "strong" | "weak" | "none" — quality of retrieval
      - top_score: float — top reranked similarity score
      - model: the synthesizer model used (e.g. claude-haiku-4-5)
      - reason: set when answer is None (e.g. "no_relevant_docs")
      - results: raw post-cutoff documents (same shape as fillin_query)
      - cutoff, query, gap_days: echoes for context

Input Schema

TableJSON Schema

Name	Required	Description
`k`	No	Number of documents to ground the answer in (1-20).
`query`	Yes	Natural-language question, max 512 chars.
`cutoff`	Yes	Training cutoff as ISO-8601 date (e.g. 2026-01-01).

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover read-only, open-world, and idempotent hints, so the bar is lower. The description adds useful behavior: the synthesis pass, higher cost than fillin_query, output quality fields (corpus_match, top_score), and the case where answer is None with a reason. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a bolded Returns block and clear use-case paragraphs. Every section contributes meaning, though the explicit return-field enumeration partially duplicates an existing output schema, making it slightly longer than necessary.

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, output schema, and annotations, the description covers purpose, usage guidance, cost behavior, and salient return semantics. It is fully sufficient for an agent to select and invoke the tool 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%, with each of the three parameters fully documented (types, defaults, constraints). The description reinforces that the query is a natural-language question and k grounds the answer, but it adds no new per-parameter semantics beyond the schema, so baseline 3 is appropriate.

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 server-side synthesis pass that returns a cited answer, and it explicitly differentiates from fillin_query by naming the alternative and contrasting the synthesis approach. The phrase 'Synthesized post-cutoff answer with inline citations' gives a specific verb+resource framing.

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 states explicit when-to-use conditions (small/cheap/weaker models like Llama, Gemini Flash, Mistral, Nemotron, Qwen), gives a clear exclusion ('Premium models ... usually get better results from fillin_query'), and provides a cost trade-off. This is model guidance with named alternatives.

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

All Fillin 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

A3.9/5.0

Disambiguation2/5

Several tools overlap significantly: fillin_query, glyph_search, and retrieve_auto all perform post-cutoff retrieval and differ only in output substrate, and fillin_health and fillin_stats both report corpus stats. This creates ambiguity for agents choosing between them.

Naming Consistency3/5

Tool names mix three conventions: fillin_* (fillin_query, fillin_mint), query_* (query_cves, query_papers), and bare names (encode, glyph_search, retrieve_auto). While readable and mostly snake_case, the lack of a uniform prefix or verb pattern makes naming inconsistent.

Tool Count4/5

14 tools is within the acceptable range for a multi-feature server, but there is some redundancy (two health/stats tools, three retrieval variants), making the count feel slightly inflated.

Completeness5/5

The server covers retrieval (text/glyph/auto), encoding, marketplace operations (mint, search, buy), and domain-specific queries (CVEs, frontier AI, markets, papers), with no obvious missing capabilities.

Resources

Need Help?