Skip to main content
Glama

Say what a document is about

sum_up
DestructiveIdempotent

Leaves a private summary and notes on a long document so the next agent knows what it says and where things are; later writes mark it stale.

Instructions

Leave a summary and notes on a document for the next agent, kept on this machine only and unseen by the person; a later write marks it stale. Write it after reading a long document, never instead, saying what it says.

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": {
      "doc": "<doc>"
    },
    "name": "sum_up"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesThe document's id from `docs`, not its title
notesNoWhat working with it needs: which section holds what, what is stale or missing
summaryNoWhat it says and what a reader comes to it for, in a few lines

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.43.2
    • changedInput schema / properties / doc / description
      Previous value: -"The document's id, as `docs` hands it back — an opaque name like `q7ntmzbm-0001`, not its title"New value: +"The document's id from `docs`, not its title"
    • changedInput schema / properties / notes / description
      Previous value: -"What the next agent should know about working with it — which section holds what, what is out of date, what it is missing"New value: +"What working with it needs: which section holds what, what is stale or missing"
    • changedInput schema / properties / summary / description
      Previous value: -"What the document says and what a reader would come to it for, in a few lines"New value: +"What it says and what a reader comes to it for, in a few lines"
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

The annotations already declare this as a mutating, destructive, idempotent, local-only operation, and the description adds genuinely useful context: the data stays on this machine, is unseen by the person, and a later write marks prior content stale. However, it never states that an existing `summary` or `notes` value is overwritten, which is the concrete destruction implied by destructiveHint=true. It also says nothing about what the call returns.

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?

Two compact sentences with the action scoped up front and the constraint trailing. The closing phrase 'saying what it says' is slightly circular, but no sentence is wasted.

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 tool with full schema coverage, no output schema, and rich annotations, the description covers what is written, where it lives, who can see it, when to use it, and staleness. The remaining gap is overwrite behavior on an existing summary, which matters given destructiveHint=true.

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 100%, so the schema already explains all three parameters including the `doc` id versus title distinction. The description only paraphrases the intent of `summary` ('saying what it says') and does not add format, length, or content guidance beyond the schema. Baseline 3 is appropriate.

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 gives a concrete verb and resource: leave a `summary` and `notes` on a document for the next agent. That distinguishes it from the nearby `note`, `append_doc`, and `reword_note` siblings, which touch the document body or existing notes rather than authored annotation fields. It is clear but stops short of explicitly contrasting itself with those siblings by name.

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

Usage Guidelines4/5

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

It gives an explicit timing rule ('after reading a long document') and an explicit exclusion ('never instead'), which is the meaningful misuse case for a summarizing tool. What is missing is guidance on when not to bother at all (e.g. short documents) and whether repeat writes should be made.

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