Skip to main content
Glama

summarize_output

Condenses large logs, command output, and file dumps into short summaries using a local Ollama model, keeping full text out of the caller's context.

Instructions

Condenses large text (logs, command output, file dumps) into a short summary using a local Ollama model, so the full text never has to enter the caller's own context. Pass text, or repository_root + path to read a file inside the bridge.

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": "summarize_output"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoFile (log, source) under repository_root, read here so it stays out of the caller's context. Max 2 MB.
textNoThe large text to summarize. Omit when using repository_root + path.
focusNoWhat to focus on, e.g. 'errors and failing tests only'.
modelNoThe Ollama model tag to invoke. Use list_ollama_models to see what's pulled.qwen-context:h-q4_0-24k
formatNoConstrain output: "json" for any JSON, or a JSON Schema object to force an exact shape.
num_ctxNoContext override; inherits the model setting when omitted.
timeout_msNoRequest deadline in milliseconds; defaults to the server's configured deadline (120 seconds by default).
num_predictNoOutput ceiling override; defaults to the smaller of the saved model ceiling and 8192 tokens.
repository_rootNoAbsolute directory that confines `path`; required with `path`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description must carry behavioral disclosure, and it does add real value: the work happens locally, the source text is read inside the bridge so it never enters the caller's context, and the file path is confined by repository_root. It says nothing about latency, model-selection consequences, failure behavior, or whether the response includes anything beyond the summary text.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Two sentences, front-loaded with what the tool does and why it matters, then the invocation modes. There is no filler and each clause carries information.

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

Completeness3/5

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

For a nine-parameter tool with no annotations and no output schema, the description covers the purpose and the two input paths but leaves out the return shape (bare summary string vs. structured result) and any cost/latency expectations. An agent could call it correctly, but not predict its output.

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 description coverage is 100%, so the schema already documents all nine parameters including focus, format, model, num_ctx, and timeout_ms; the baseline of 3 applies. The description reinforces the mutually exclusive text vs repository_root+path pattern but adds no meaning beyond the schema for focus, format, or the token/context overrides.

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?

States a concrete verb and resource ('condenses large text ... into a short summary') plus the engine ('local Ollama model') and the benefit (text stays out of the caller's context). It clearly implies a different role from read_symbol/outline_file by never returning raw text, but it does not explicitly name a sibling or draw the boundary against run_ollama_task.

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?

The description gives the two input modes ('Pass `text`, or `repository_root` + `path`'), which implicitly tells an agent how to call it. It never states when to prefer this over run_ollama_task or plain file reading, and offers no when-not-to-use guidance such as small inputs where summarization is wasteful.

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