Skip to main content
Glama

Firecrawl by Nova (CIVAI)

alexandria_library_search

Find the data source for the task first: grep -ril "<word>" /library lists the capabilities that cover it. For a step-by-step workflow (sales or meeting prep, prospect lists, competitor, market or financial research, monitoring) or to explore, check /library/skills: cat /library/skills/search/<a-few-words-from-the-task> (joined by hyphens) ranks the skills, your team's first; cat the path to read one. Explore the Alexandria library: Firecrawl's catalogue of data providers that return typed, sourced records (companies, people, jobs, finance and filings, public records and government spending, real estate, places and restaurants, retail and prices, package registries and developer data, news, research, and more) as a read-only filesystem, using shell commands. Use this to find out whether a provider covers the data a task needs, and to read its contract before alexandria_library_read. Layout: /library///.md, one file per capability holding its contract (when to use it, inputs, outputs, and the call to send); /library, each category folder and each provider folder has a README.md describing what is inside. Category folders: agriculture, ai-models, apps, automotive, community, companies, developer, digital-intelligence, education, energy, entertainment, finance, game-development, government, health, healthcare, jobs, knowledge, life-sciences, marketing, music, news, people, places, podcasts, political-science, real-estate, research, restaurants, shopping, social, software, sports, travel; ls /library shows any added since. Available commands: ls, tree, cat, head, tail, grep, find, wc, sort, uniq, cut, tr, sed, jq, xargs, with pipes. Typical starts: ls /library, cat /library/README.md, or grep -ril "mortgage" /library. A file path is the execute address: /library/finance/fred/series/observations.md is provider "fred", capability "series/observations". Recorded example responses are under /examples//.json. Free; does not run providers.

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": {
      "command": "<command>",
      "objective": "<objective>"
    },
    "name": "alexandria_library_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYesShell command to run inside the read-only library, e.g. `grep -ril "rental" /library | head -20`.
objectiveYesThe 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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / objective / description
      Previous value: -"The user's underlying goal for this call, in one sentence: what they are ultimately trying to accomplish, not a restatement of the URL or query. Reuse it across related calls. Avoid sensitive information."New value: +"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."
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden and does so: read-only filesystem, free of charge, does not execute providers, no permission or auth requirements, and an explicit allow-list of shell commands (ls, tree, cat, head, tail, grep, find, wc, sort, uniq, cut, tr, sed, jq, xargs, with pipes). It also discloses the filesystem layout and where recorded example responses live (/examples/<provider>/<capability>.json), which is exactly the kind of context annotations would otherwise need to provide.

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

Conciseness3/5

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

The useful content is front-loaded (find the source, then read the contract), but the middle is dense and sprawling, and the 33-item enumeration of category folders largely duplicates what `ls /library` already reveals. Sentences chain multiple clauses with semicolons, making it harder to scan than a structured list of purpose, workflow, and commands would be.

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 a 3-parameter shell-over-filesystem tool with no annotations and no output schema, the description covers layout, discovery commands, path-to-provider mapping, and example response locations — enough to act correctly without further context. The gap is that it never says what a result looks like (file paths? contract text?) or whether reads are truncated, which matters for a `cat`/`head`-driven tool with no output schema.

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 baseline is 3, but the description adds meaning beyond the schema: it shows the shape of a valid `command` ("grep -ril \"rental\" /library | head -20", pipes allowed) and explains the addressing semantics of a path as provider plus capability. It does not add much on `objective` or `conversationId` beyond what the schema already states, hence 4 rather than 5.

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 concrete verb and resource chain: "Explore the Alexandria library: Firecrawl's catalogue of data providers ... as a read-only filesystem, using shell commands," and explicitly frames it as the pre-read discovery step ("to find out whether a provider covers the data a task needs, and to read its contract before alexandria_library_read"). It also disambiguates its address space ("A file path is the execute address") and its output kind (contracts, not data), which an agent could not infer from the name alone.

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?

Gives explicit when-to-use conditions ("Find the data source for the task first", "before alexandria_library_read", workflow tasks like sales or meeting prep, competitor or financial research), a named alternative (alexandria_library_read), and concrete entry points ("ls /library", "cat /library/README.md", "grep -ril \"mortgage\" /library"). It also states an implicit exclusion — the tool "does not run providers" — so the agent knows this is lookup, not execution.

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