Skip to main content
Glama

Firecrawl by Nova (CIVAI)

firecrawl_search_feedback

Firecrawl uses this feedback to find and fix results that were wrong, missing or unhelpful, which improves the data later calls return.

Records schema-validated quality feedback for a prior firecrawl_search UUID searchId. A good rating requires a valuable result or a valuable source, partial either of those or at least one missingContent entry, and bad at least one missingContent entry or a query suggestion; caps are 50 valuableResults, 50 valuableSources, and 20 missingContent entries.

Eligibility is limited to successful searches within the feedback age window. The record is idempotent per search ID. Eligible first feedback for a search can refund 1 credit; refunds are subject to the team's daily cap. The response reports whether a refund was applied, along with submission and daily-cap status.

Mark useful returned results in valuableResults as {"source", "position"} copied off the result. Groups are numbered from 1 independently, so {"source":"web","position":1} and {"source":"news","position":1} are different results. Be exhaustive — results you do not list are treated as not useful. Reserve valuableSources for useful URLs that were NOT among the returned results; never report one result in both fields.

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": {
      "searchId": "<searchId>",
      "rating": "<rating>"
    },
    "name": "firecrawl_search_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
ratingYes
searchIdYes
objectiveNoThe user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words.
conversationIdNoconversationId from any earlier Firecrawl tool result in this conversation; after parallel calls, any one of theirs. Omit only on the first call of a conversation; the result returns one to pass on every later call.
missingContentNoArray of specific pieces of content the agent expected to find but did not. One entry per distinct topic. Each entry has a short `topic` and optional longer `description`.
valuableResultsNoEvery result that was actually useful, copied from the `source` and `position` stamped on each result. Each group is numbered from 1 independently, so the source is required — `{"source":"web","position":1}` and `{"source":"news","position":1}` are different results. Be exhaustive — unlisted results are treated as not useful. Do not also list the same results in valuableSources.
valuableSourcesNo
querySuggestionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / objective
      Added value: +{
      +  "description": "The user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words.",
      +  "maxLength": 5000,
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full disclosure burden and does so: idempotency per search ID, the one-credit refund on eligible first feedback, the team daily cap, and the fact that the response reports refund and cap status. It also discloses the consequential side effect that unlisted results are treated as not useful, which materially shapes how an agent must fill the payload.

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?

It is front-loaded with purpose, then rules, then field mechanics, and most sentences earn their place. The opening sentence about Firecrawl fixing wrong results is motivation rather than instruction, and the density across four paragraphs is near the upper limit, but nothing is redundant.

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?

For an 8-parameter mutation tool with no annotations and no output schema, the description covers eligibility, idempotency, refund economics, response shape, and the two hardest array parameters. Minor gaps remain: `querySuggestions` is never explained in the description, and the precise meaning of the feedback age window is unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50%, but the description compensates heavily: it explains the {source, position} tuple for valuableResults, the per-group independent numbering with a worked example, the exclusivity rule against valuableSources, per-field caps (50/50/20), and the rating-conditional requirements. This is meaning the schema alone would not convey.

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 states a specific verb and resource — 'Records schema-validated quality feedback for a prior `firecrawl_search` UUID `searchId`' — which pins the action to a concrete object and ties it to a named sibling tool. An agent can distinguish this from the generic `firecrawl_feedback` sibling because the targeting key is explicitly a search ID.

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?

It gives explicit eligibility conditions (successful searches only, within the feedback age window) and concrete rules for choosing each rating: good needs a valuable result or source, partial needs those or a missingContent entry, bad needs a missingContent entry or query suggestion. It also instructs how to allocate entries between valuableResults and valuableSources. The only gap is no explicit statement of when to prefer this over the sibling `firecrawl_feedback`.

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.

Resources