Skip to main content
Glama

Read bounded incremental task events (read-only)

dsh_get_events
Read-onlyIdempotent

Read task event log pages with an opaque cursor to inspect delegated run progress; bounded, read-only, and secrets scrubbed.

Instructions

Reads at most limit (default 25, hard cap 100) events from the task event log, starting at an opaque cursor. Logs are scanned in bounded chunks, never loaded whole; a trailing partial JSONL line is not consumed. Cursors are bound to task id and file identity, and invalid/cross-task/stale cursors are refused. Live and persisted-history reads are read-only: no PID is probed or controlled, no runtime is started and no model request is made. Secrets are scrubbed and model reasoning is stripped at output as well as storage.

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": {
      "taskId": "<taskId>"
    },
    "name": "dsh_get_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum events in this page. Default 25, maximum 100.
cursorNoOpaque nextCursor from a previous dsh_get_events page.
taskIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.8

TDQS

A4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, closed-world, non-destructive behavior, yet the description still adds substantial context: bounded chunk scanning without loading the whole log, a trailing partial JSONL line being left unconsumed, cursors bound to task id and file identity, and invalid/cross-task/stale cursors being refused. It also discloses that secrets are scrubbed and model reasoning stripped at output, and that no PID is probed or runtime started.

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?

The core action and bounds are front-loaded in the first clause, and each following sentence carries distinct operational information (chunking, cursor validity, read-only guarantees, output scrubbing). It is a single dense paragraph, so scanning is slightly harder than a bulleted layout, but no sentence is filler.

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 three-parameter read tool with no output schema, the description covers pagination mechanics, failure modes, and safety guarantees well. The remaining gap is the shape of a returned event (fields an agent would receive) and whether a nextCursor is always present, which would help since no output schema documents it.

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 67%, and the description genuinely extends it for 'cursor': cursors are opaque, bound to task id and file identity, and refused if invalid, cross-task, or stale — behavior an agent cannot read off the schema. The limit bound (25 default, 100 cap) is restated from the schema, and taskId receives no added meaning, keeping it below a 5.

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

Purpose4/5

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

The description opens with a specific verb and resource: 'Reads at most limit ... events from the task event log,' plus the pagination mechanism (opaque cursor). It clearly delimits scope to the event log rather than results or history, though it never names a sibling tool to contrast with, so differentiation from dsh_get_result or dsh_get_history is inferred 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?

Pagination usage is implied by 'starting at an opaque cursor' and the note that cursors come from a previous page, which tells an agent how to iterate. However, there is no explicit statement of when to use this tool versus dsh_get_result, dsh_get_history, or dsh_wait_task, and no stated exclusions.

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