Skip to main content
Glama

Try a skill: real capped public replay

try_skill

Runs a real browser replay on a public site; capped; non-destructive allowlisted skills only. No token or identity needed. On the remote endpoint it takes two calls: the first returns a short challenge question (challenge_id); call again with the same slug and inputs plus challenge_id and answer. In the local server it is one call (it solves the node's proof of work itself). Returns run_id, the run page and a poll hint; when the run completes, run_record is the signed run record cid (check it with verify_record). Skills with a recorded action trace replay deterministically: 0 model calls, and the result includes value (the answer read off the page) and model_calls. Limits: a few runs per network per day and a small node-wide daily budget. When a limit is reached (or public replay is switched off) it returns the latest verified run of that skill instead, marked status: cached (not a new replay), with its signed record cid and run page. For your own uncapped runs use run_skill in the local server.

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": {
      "slug": "<slug>"
    },
    "name": "try_skill"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugYesskill slug from find_skill (only skills with public_replay: true)
answerNoyour answer to the challenge question
inputsNoa value for every param the skill lists (see get_skill); new values are welcome
paramsNosame as inputs (run_skill's name for them)
challenge_idNofrom the first try_skill call
wait_secondsNowait up to this long for the run to finish (default 60; 0 returns the run_id right away)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / params
      Added value: +{
      +  "additionalProperties": {
      +    "type": "string"
      +  },
      +  "description": "same as inputs (run_skill's name for them)",
      +  "propertyNames": {
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.6/5.0
Behavior4/5

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

Rich disclosure beyond the annotations: rate limits (a few runs per network per day plus a node-wide daily budget), the two-call challenge/answer protocol on the remote endpoint versus one call locally, and the degraded cached fallback path marked status: cached. The "non-destructive" claim is consistent with destructiveHint=false and the openWorldHint matches the public-site replay. Only the return-shape timing (wait_seconds vs polling via skill_run_status) is left somewhat implicit.

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?

Dense but front-loaded: the purpose leads, followed by the call protocol, returns, limits, and the run_skill alternative. Every sentence carries information, but the long semicolon-chained first sentence and the mid-paragraph return-value detail make it harder to scan than it could be.

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?

Despite no output schema, the description covers the return payload (run_id, run page, poll hint, run_record cid, value, model_calls) and points to verify_record for validation. For a mutation-flagged, open-world tool with 6 params, nothing an agent needs to call it correctly is missing.

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 genuinely new meaning by explaining the pairing of challenge_id and answer in the two-call remote sequence, which the schema only hints at individually. It also implies inputs/params must cover every parameter the skill lists, though it does not clarify why both aliases exist.

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?

Specific verb and resource ("Runs a real browser replay on a public site") with explicit scope constraints (capped, non-destructive, allowlisted-only, public_replay skills). It is clearly distinguished from its sibling tool run_skill (uncapped local runs) and from read-only siblings like get_skill or verify_record.

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 when to use this versus the alternative ("For your own uncapped runs use run_skill in the local server") and names the prerequisite flow (slug from find_skill with public_replay: true). It also tells the agent when results are not a fresh run: on hitting limits it returns a cached record instead.

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.