Skip to main content
Glama

book_documents_act

One action on one open document (ZEN-2): an action its row offers, with its version.

accept posts the held proposal; reject closes it unposted (a person books the document); keep, reanalyze, mark_irrelevant, delete; skip / unskip leave it to a person. All but accept and unskip need a reason. Recorded with your user; an agent decides a hold only where the owner allowed it. Returns the new status.

On this MCP surface a null argument means "not provided": it is dropped before the request is sent, exactly as if the field were omitted.

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": {
      "company_id": "<company_id>",
      "decision_id": "<decision_id>",
      "action": "<action>",
      "version": "<version>"
    },
    "name": "book_documents_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
reasonNo
versionYes
company_idYes
decision_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does add real context: actions are recorded against your user, an owner-level permission gate constrains agent decisions, a reason is mandatory for most actions, and the call returns the new status. It never says whether delete or reject is reversible, what happens on a version mismatch, or what error/conflict behavior to expect. Useful but not complete for an unattended mutation tool.

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 a single-sentence statement of scope, followed by action semantics and then a qualifier about null handling. Dense but every clause carries meaning; the internal tag 'ZEN-2' is the only unearned token. The null-argument note is placed last, which is reasonable for an edge-case rule.

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 5-parameter, 4-required mutation with no annotations and no output schema, the description should fully cover the action vocabulary and identifiers. It misses the 'ignore' action, leaves company_id and decision_id undefined, and does not address version-conflict or failure behavior, though 'Returns the new status' does spare it an output explanation.

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 0%, so the description must compensate, and it partially does: it ties reason to all actions except accept and unskip, explains that version accompanies the action, and clarifies that a null argument is dropped before the request. However, it omits the enum value 'ignore' entirely and says nothing about company_id or decision_id, leaving two required identifiers unexplained. That gap is material at 0% coverage.

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 specific verb and resource: one action on one open document, with the action vocabulary enumerated. An agent knows immediately this is a per-decision mutation rather than a list/get tool. It stops short of naming a sibling for differentiation, so it is clear but not fully disambiguated from tools like accept_autopost_decision.

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?

Gives clear context for choosing among the action values: accept posts a held proposal, reject closes it unposted and hands it to a person, skip/unskip leave it to a person, and all but accept and unskip require a reason. It also flags that an agent may only decide a hold where the owner allowed it. It offers no explicit 'use this instead of X' routing, which keeps it below a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources