Skip to main content
Glama

cortex_peek

Read-onlyIdempotent

Extract targeted page controls, grid records, or field values via returned refs and optional CSS scope; refresh refs after navigation or AJAX updates.

Instructions

Controlli/griglie o estrazione mirata. Usa i ref restituiti; dopo navigazione o sostituzione AJAX aggiorna quelli necessari. scope opzionale: CSS di un solo contenitore verificato. items: CSS dei record ripetuti. fields maxLength 1..500 (default 300). Niente HTML o valori input.

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": "cortex_peek"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNocontrols
frameNo
itemsNo
limitNo
queryNoFiltra anche per testo della riga. Per scegliere una sua azione cerca il record e usa il ref del controllo restituito.
scopeNoCSS di un solo contenitore verificato. Opzionale: omettere se sconosciuto. Per elementi ripetuti usare items o each, non scope.
fieldsNo
offsetNo
timeoutNo
sessionIdNoID restituito da newSession. Omettere per usare la sessione condivisa.
tableOffsetNo
project_pathNo
waitForReadyNoAttende fetch/XHR attivi, jQuery e aria-busy. false consente fotografia parziale, segnalata incomplete.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0-dev.1

TDQS

B3.1/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), yet the description adds genuine behavioral context beyond them: refs go stale after navigation or AJAX substitution and must be refreshed, and extraction is limited ('Niente HTML o valori input'), which constrains what the agent can expect back. It still does not describe the shape of the returned payload or what an incomplete/snapshot result looks like, keeping it below 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.

Conciseness3/5

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

It is short and front-loads the mode distinction, with no filler sentences. But the telegraphic, fragmentary Italian ('Controlli/griglie o estrazione mirata') trades brevity for clarity, and the scope/items/fields rules are run together without structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter, no-required-parameter tool with no output schema and low schema coverage, the description leaves too much open: the meaning of mode, the difference between limit/offset and tableOffset, the role of frame and project_path, and what is actually returned. Given the tool's complexity, more explanation is needed.

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 coverage is only 31% across 13 parameters, so the description must carry weight; it does clarify the two most confusable ones (scope = CSS of one verified container, items = CSS of repeated records) and the fields maxLength range. However, mode, frame, limit, offset, tableOffset, timeout and project_path are unexplained in both places, leaving the majority of the parameter surface undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening 'Controlli/griglie o estrazione mirata' enumerates the three modes (controls/grid/extract) and the later 'Usa i ref restituiti' hints that the tool returns refs for page elements, so an agent can loosely infer it inspects a rendered page. But no verb states the core action (read/inspect/return), and nothing distinguishes it from siblings like cortex_open or cortex_run. Purpose is guessable rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives real conditional guidance: refresh refs after navigation or AJAX replacement, use items (not scope) for repeated records, and omit scope when the container is unknown. What is missing is any routing guidance relative to cortex_open/cortex_run/cortex_debug, so the agent must infer when to peek versus open or run.

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

Deploy Server

Other Tools