Skip to main content
Glama

What is in a document

outline_doc
Read-onlyIdempotent

Retrieve a document's headings, pages, length, and structure signals first so you can plan edits or choose which sections to read before changing long documents.

Instructions

A document's headings with their at, lines and size, its length and print, and its pages with title, length and sections: a few hundred tokens. Ask it first for a long document or a change in part. Also pointed_at (who links here), by (agent or person) and the signs it wants compacting: alike, repeated, dead, mislabeled, loose.

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": "outline_doc"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesThe document's id from `docs`, not its title

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field 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"
  2. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new behavior: the cost bound ('a few hundred tokens') and the scope of what is surfaced, including backlink and authorship metadata and detected compaction problems. It omits any note on truncation or how the compaction signals should be acted on, which keeps it from 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 compact and information-dense, but front-loads a run-on field inventory instead of the tool's purpose, and leaves several backticked field names (`at`, `print`, `alike`, `loose`) semantically opaque without glosses. The reader has to reconstruct meaning rather than being told it.

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?

With no output schema and only one simple parameter, the description carries the return-value burden and does so across headings, pages, backlinks, authorship, and compaction flags. Coverage is broad enough to call the tool correctly, though the terse field glosses leave some output details ambiguous.

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?

There is a single parameter with 100% schema coverage, and the schema already states that `doc` is the id from `docs` rather than the title. The description adds nothing further about the parameter, so baseline 3 applies.

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 description enumerates what comes back (headings, length, pages, backlinks, author, compaction signals) rather than stating a verb+resource such as 'returns an outline of a document.' An agent can infer the purpose from the field list, but the tool's identity is implied, not asserted, and no sibling such as read_doc, page_doc, or docs is named for contrast.

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?

'Ask it first for a long document or a change in part' gives a clear triggering condition: use as a cheap first pass before deeper retrieval, and when only part of a document changed. It stops short of naming the specific alternative tool to use afterward, so it is context-rich but not fully routing-explicit.

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