Skip to main content
Glama

Firecrawl by Nova (CIVAI)

firecrawl_save_skill

Create or change one of the user's team skills: instructions an agent follows, naming capabilities as @provider/capability. Without id, creates one: write name, description and body, or copy a skill under /library/skills with from (its id: for /library/skills/firecrawl/, team: for /library/skills/team/); fields you also give override the copy, and a library skill copies its SKILL.md only. The new skill is enabled and listed in /library/skills/INDEX as /library/skills/team/; a taken slug is a conflict. With id (team:) and baseVersion, the version: in its SKILL.md, changes its name, description or body (a new version), or whether it is enabled or listed; a skill changed since is refused with conflict, so read it again and reapply. A body edited from the text you read must write each capability as @provider/capability again: the plain code it shows saves no reference. Library skills cannot be changed; copy one. Skills cannot be deleted here. Returns the saved skill's path and the command that reads it. Save only what the user asked for. Free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "firecrawl_save_skill"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoUpdate: the team:<slug> skill to change. Omit to create a skill.
bodyNoThe instructions in full, in Markdown; required to create without from. Reference capabilities as @provider/capability.
fromNoCreate: the skill to copy, by id: <id> for /library/skills/firecrawl/<id>, team:<slug> for /library/skills/team/<slug>. Fields you also give override the copy.
nameNoSkill name; required to create without from.
slugNoCreate: lowercase words joined by hyphens; defaults to one made from the name.
enabledNoUpdate: turn the skill on or off.
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.
baseVersionNoUpdate, required: the version: in the skill's SKILL.md. A skill changed since is refused with conflict: read it again and reapply.
descriptionNoWhen to use the skill; required to create without from.
discoverableNoUpdate: whether /library/skills/INDEX lists it.

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. Added

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses optimistic concurrency (stale baseVersion is refused with conflict), slug collision as a conflict, immutability of library skills, no deletion, default post-create state (enabled and listed in INDEX), copy semantics (library skill copies only its SKILL.md, supplied fields override), a non-obvious gotcha about capability references on edited bodies, the return value ('the saved skill's path and the command that reads it'), and that the call is free.

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?

Very little is wasted, but the whole definition is one semicolon-chained paragraph with nested parentheses, mixing create, copy, update, and constraint rules in a single block. Front-loading the create/update split helps, yet the dense run-on makes it hard to scan for the one branch an agent needs.

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 10-parameter mutation tool with no annotations and no output schema, the description covers create/update/copy branches, conflict behavior, and the return value. What it leaves out is peripheral: permission requirements and error behavior for cases other than slug or version conflicts.

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 each field; the description adds genuine meaning on top by explaining interactions the schema states only per-field: from combined with overrides, baseVersion tied to the 'version:' line in SKILL.md, and toggling enabled/discoverable only under an update. It never explains the objective parameter, which the schema must carry alone.

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 ('Create or change one of the user's team skills') and immediately defines what a skill is ('instructions an agent follows, naming capabilities as @provider/capability'), then splits the two modes by the presence of id. An agent knows exactly what this tool produces without opening the schema.

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?

Explicit routing rules: omit id to create, supply id plus baseVersion to update, use from to copy a library skill, and 'Library skills cannot be changed; copy one' plus 'Skills cannot be deleted here' are stated exclusions. It also requires a read-before-write loop ('read it again and reapply') and adds a scoping rule ('Save only what the user asked for').

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