Skip to main content
Glama
smallest-inc

Smallest MCP Server

Official
by smallest-inc

add_agent_tool

Add or update one or more HTTP API tools on a single-prompt agent, enabling it to make external requests (e.g., look up orders, post to CRM) during calls. Tools upsert by name.

Instructions

Add (or update) one or more API-call tools on a single_prompt agent. API-call tools let the agent make an HTTP request to an external API during a call — e.g. look up an order, book an appointment, or post to a CRM. The agent decides when to invoke a tool based on its name and description, filling in any declared parameters. Pass a single tool via the top-level fields, or several at once via tools (preferred when configuring multiple tools — they land in one draft write). Upserts by name: tools with existing names are replaced; others are added (existing tools are preserved). For versioned agents the change is saved as a draft — pass draft_id to stack onto an existing draft (e.g. one returned by update_agent_prompt or set_pre_call_api) instead of creating a new one, then publish_draft once. Caveat: the draft's tools section is written wholesale, so when targeting a draft that already had tool edits, include ALL desired tools in this call. Use get_agent_prompt to see an agent's current live tools.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agent_idYesThe agent ID to add the tool(s) to
draft_idNoExisting draft to write into (stacks this change onto the draft's other edits). Omit to create a new draft from the live version.
toolsNoBatch mode: multiple API-call tools to add/update in one write. When provided, the top-level single-tool fields are ignored.
nameNoUnique tool name, no spaces (e.g. lookup_order). Re-using a name replaces that tool.
descriptionNoWhat the tool does and when the agent should call it. This is the only guidance the LLM gets — be specific.
urlNoThe endpoint URL to call. May contain {{variable}} placeholders.
methodNoHTTP method
timeout_msNo
headersNo
query_paramsNo
request_bodyNo
parametersNo
response_variablesNo
enabledNo
Behavior4/5

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

With no annotations, the description carries full weight. It discloses upsert-by-name behavior, draft wholesale overwrite, and the fact that the agent decides invocation based on name/description. It doesn't cover rate limits or auth, but the key behavioral traits (single vs batch, draft stacking) are well explained.

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?

The description is a single paragraph of moderate length but every sentence contributes information. It is front-loaded with the core action and progressively details important nuances (upsert, draft behavior). While not extremely concise, it is well-structured and avoids redundancy.

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?

Given the complexity (14 parameters, no output schema, no annotations), the description covers all essential aspects: tool purpose, input modes, upsert behavior, draft management, parameter referencing, and response variable extraction. It lacks mention of authentication or error handling, but for the tool's function, it is sufficiently complete.

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?

Despite 50% schema description coverage, the description adds significant value beyond the schema. It explains the distinction between single-tool fields and the `tools` array, the role of `draft_id` for stacking, and how parameters like `name` and `description` guide the LLM. The schema already describes each field, but the narrative clarifies usage patterns.

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?

The description clearly states the action (add/update) and resource (API-call tools on a single_prompt agent). It distinguishes from sibling tools like remove_agent_tool by focusing on adding/updating, and provides examples of tool usage (look up order, book appointment) that clarify purpose.

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?

The description explains when to use (adding/updating API-call tools) and provides context about upsert behavior and draft management. It doesn't explicitly say when not to use, but it mentions an alternative (get_agent_prompt) for viewing live tools, and the context of sibling tools implies removal is separate. The guidance on drafting (pass draft_id to stack, publish_draft) is clear.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/smallest-inc/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server