Skip to main content
Glama
overseer-nvim-mcp

overseer-nvim-mcp

Tail overseer task output

overseer_tail
Read-only

Stream a task's live output with a status line, using since to fetch only new lines and wait_for to block until a regex matches or the task exits.

Instructions

Return a task's live output, preceded by a status line. task is a numeric id or a case-insensitive name substring; omit it for the most recent task. The status line reports status, exit_code once the task has exited, and total (lines available so far), so you never need a separate overseer_list_tasks to find out whether what you are tailing is still alive. Pass the previous total back as since to get only what is new instead of re-reading the same lines; from tells you where the returned block actually starts, and a from greater than since + 1 means output scrolled past between calls. Set wait_for to a regular expression to block until a matching line appears; use it instead of polling repeatedly. It returns as soon as it matches, or when the task exits, or at timeout_ms (default 15000, max 120000), and reports which of the three happened as waited, so a timeout is never mistaken for success. wait_for is for a wait of a few seconds. This call cannot be backgrounded, so a longer one holds up the conversation for the task's whole duration; wait for those with the wait subcommand in your shell instead, as the server instructions describe.

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": "overseer_tail"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskNo
linesNoTrailing lines to return; default 10. Pass more when diagnosing a failure, e.g. 100 for a stack trace with its footer
sinceNo
wait_forNo
timeout_msNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.1
    • addedInput schema / properties / lines / description
      Added value: +"Trailing lines to return; default 10. Pass more when diagnosing a failure, e.g. 100 for a stack trace with its footer"
  2. First observedv0.2.0

TDQS

A4.7/5.0
Behavior4/5

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

Goes well past the readOnlyHint annotation: it discloses blocking behavior, the three ways the call can return (match, task exit, timeout) and that the outcome is reported as `waited` so a timeout is not mistaken for success, plus default and maximum timeout values. It also warns that the call cannot be backgrounded and holds up the conversation. The only gap is the near-omission of `lines` behavior in prose, which the schema covers anyway.

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?

Front-loaded with purpose and the status line, then parameters, then wait semantics, then the blocking caveat — a sensible order. It is dense, single-paragraph and long, but nearly every clause is load-bearing; only minor tightening (e.g. the `from`/`since` explanation) would improve it.

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?

For a no-output-schema, 5-parameter read tool with five sibling alternatives, the description covers input meaning, return shape (status line fields `status`, `exit_code`, `total`, plus `from` and `waited`), and the operational cost of blocking. Nothing an agent needs to call it correctly or interpret the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 20% (just `lines`), so the description carries most of the burden and does: `task` accepts a numeric id or a case-insensitive name substring, `since` should be the previous `total`, `wait_for` is a regular expression, and `timeout_ms` defaults to 15000 with a 120000 ceiling. It also explains the relationship between `since` and `from` and what a gap of more than one means, which is meaning no schema field conveys.

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?

Opens with a specific verb and resource ('Return a task's live output, preceded by a status line') and explicitly differentiates from the sibling `overseer_list_tasks`, explaining that the status line makes a separate listing call unnecessary. An agent can distinguish this from the list/stop/dispose siblings without opening any 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?

Gives explicit conditions: omit `task` for the most recent task, pass `since` to read incrementally instead of re-reading, use `wait_for` instead of polling, and use the shell `wait` subcommand rather than this call for long waits. It also states the scope of `wait_for` ('a wait of a few seconds'), which is a real exclusion rule rather than a vague hint.

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