Skip to main content
Glama
Sign In

fillprompt

by com.fillprompt
OverviewDiscussionsAdmin

Search prompts

search_prompts
Read-only

Search over 6,700 free, ready-to-copy AI prompts on fillprompt.com: image prompts (GPT Image, Nano Banana, Midjourney and more), video prompts (Seedance, Veo, Kling and more) and text prompts (system prompts, agent prompts, roles). Returns titles, page URLs and short previews; call get_prompt for the full text.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_prompts"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoOnly image, video or text prompts.
limitNoHow many results to return.
modelNoOnly prompts written for this AI model, e.g. "Nano Banana", "Seedance", "Claude". See list_filters.
queryYesWhat the prompt should make, in plain words, e.g. "coffee product photo on marble" or "code review agent".
categoryNoImage category (e.g. "product-brand", "poster") or text prompt type (e.g. "agent", "developer"). See list_filters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds what the agent actually needs beyond that — the return shape (titles, page URLs, short previews) and the explicit handoff to get_prompt. It does not mention ranking, result quality or pagination behavior, which keeps it from a 5.

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?

One front-loaded sentence states the corpus and content types, followed by a short clause on returns and the next step. The parenthetical model lists are slightly dense but earn their place by signalling filterable values. Nothing is redundant.

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 no output schema, the description correctly compensates by describing the return fields and pointing to get_prompt for full content. Corpus size, content types, filter hints and the retrieval workflow together cover everything an agent needs to call this 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 all five parameters carry their own descriptions and enum definitions. The description only maps content types to the type filter at a high level and adds no syntax or format guidance beyond the schema, which is the expected baseline when the schema does the heavy lifting.

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?

States a specific verb and resource (search prompts) plus the corpus scope (6,700 prompts on fillprompt.com) and enumerates the searchable content types (image, video, text) with example models. The closing pointer to get_prompt for full text makes it unambiguous how this differs from its sibling.

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?

Clearly establishes the search-then-fetch workflow: this tool returns titles, URLs and previews, and get_prompt is named as the follow-up for full text. It also defers valid filter values to list_filters via the schema, so no alternative is left ambiguous. It stops short of stating when NOT to search (e.g. browsing instead of querying).

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

All fillprompt toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources