Skip to main content
Glama

Edit a bot function

dosai_update_function
Destructive

Change one function of the bot: its name, the description the model reads to decide WHEN to call it, its parameters, whether it is on, the "after this function, say nothing to the client" switch, or the "only looks things up" switch. Send only what changes. The description is the single strongest lever over a function: it is what the model sees. Address, headers, secrets and the action type are NOT editable here, they live in the cabinet. Requires editor role.

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": {
      "project_id": "<project_id>",
      "function_id": "<function_id>"
    },
    "name": "dosai_update_function"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoTechnical name the model calls, latin letters, digits and underscore.
is_activeNo
read_onlyNotrue = this function only looks things up and changes nothing (product search, stock, price list). When the client writes more while the bot is answering after such a function, the bot waits and answers everything in ONE message, calling the function again. Only for HTTP (webhook) functions, refused for built-in ones and together with "this is a lead", "say nothing", "finish the dialog" or a booking: a function that sends, books or records must never be repeated. false removes the switch.
parametersNoFull new list of parameters: it REPLACES the old one, so send every parameter you want to keep.
project_idYesFrom dosai_list_projects.
descriptionNoWhen to call this function and what it does, in the owner's words. This is what the model reads.
function_idYesFrom dosai_list_functions.
silent_after_callNotrue = after this function fires, the bot sends the client NOTHING: no text, no bubble in the dialog, and the chat is marked "reply by hand" for the owner. For a function that calls a human in and a person answers within minutes. Refused together with "this is a lead" (the lead card would not be created). false removes the switch.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / function_id / description
      Previous value: -"Function id, as returned by dosai_list_functions."New value: +"From dosai_list_functions."
  2. Changed2 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / project_id / description
      Previous value: -"Project id, as returned by dosai_list_projects."New value: +"From dosai_list_projects."
  3. Changed2 schema fields changed
    • removedInput schema / properties / function_id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • removedInput schema / properties / project_id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
  4. Changed1 schema field changed
    • changedInput schema / properties / read_only / description
      Previous value: -"true = this function only looks things up and changes nothing (product search, stock, price list). When the client writes more while the bot is answering after such a function, the bot waits and answers everything in ONE message, calling the function again. Only for HTTP (webhook) functions, refused for built-in ones and together with \"this is a lead\" or \"say nothing\": a function that sends, books or records must never be repeated. false removes the switch."New value: +"true = this function only looks things up and changes nothing (product search, stock, price list). When the client writes more while the bot is answering after such a function, the bot waits and answers everything in ONE message, calling the function again. Only for HTTP (webhook) functions, refused for built-in ones and together with \"this is a lead\", \"say nothing\", \"finish the dialog\" or a booking: a function that sends, books or records must never be repeated. false removes the switch."
  5. Changed1 schema field changed
    • addedInput schema / properties / read_only
      Added value: +{
      +  "description": "true = this function only looks things up and changes nothing (product search, stock, price list). When the client writes more while the bot is answering after such a function, the bot waits and answers everything in ONE message, calling the function again. Only for HTTP (webhook) functions, refused for built-in ones and together with \"this is a lead\" or \"say nothing\": a function that sends, books or records must never be repeated. false removes the switch.",
      +  "type": "boolean"
      +}
  6. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say destructiveHint=true; the description goes much further, disclosing partial-update semantics, the editor-role requirement, and concrete refusal rules (read_only refused for built-in functions and alongside lead/silent/booking switches). It also explains the downstream consequence of silent_after_call (no client message, chat marked "reply by hand"), which is real behavioral context an agent could not infer from structured fields.

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?

The editable-field inventory is front-loaded in the first sentence, then rules (patch semantics, non-editable fields, role requirement) follow in short declarative clauses. Every sentence carries distinct information; nothing is filler or repeated from the schema.

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 an 8-parameter destructive mutation with no output schema, the definition covers scope, patch semantics, permissions and refusal conditions well. It omits what happens on success (whether a new version is created, whether the change is applied to live traffic immediately), which matters given the sibling version/restore tools exist.

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

Parameters4/5

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

Schema coverage is 88%, so the heavy lifting is already done by the schema, but the description adds the partial-update meaning of omission ("Send only what changes") and frames description as the model-facing lever, which is semantic rather than restated. It does not add anything on name or is_active beyond the schema, so it stops short of a 5.

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?

"Change one function of the bot" is a specific verb+resource, and the description enumerates exactly which fields are in scope (name, model-facing description, parameters, on/off, silent-after-call, read-only). It further draws the boundary by naming what is NOT editable here (address, headers, secrets, action type), which separates it from configuration-oriented siblings without the agent needing to open 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 Guidelines4/5

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

"Send only what changes" gives explicit patch semantics, and "Requires editor role" states a prerequisite up front. The field-level exclusions ("NOT editable here, they live in the cabinet") tell the agent when to go elsewhere, but the pointer is vague and the overlap with a sibling like dosai_set_function_active for toggling is_active is never acknowledged.

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