Skip to main content
Glama

surf

by tech.geckovision

comprehend_api

Read-onlyIdempotent

Submit an API's OpenAPI URL (or a human docs page URL with from_docs=true) and get it comprehended into first-call-correct agent tools — no integration code. Returns the API name, its usable tools, agent-native artifacts (llms.txt / gecko.json / tools.md), and self-host next steps. Comprehends and returns to YOU only: it does not host, publicly list, or register your API.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe API's OpenAPI spec URL (or a docs page URL if from_docs).
from_docsNoRecover the surface from a human docs page instead of an OpenAPI spec. Results are quarantined pending review.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

The annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavioral context beyond that by stating the tool does not host, publicly list, or register the API, and that results are returned only to the caller. This clarifies privacy and side-effect expectations.

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 description is compact and front-loaded. The primary action and input are in the first clause, and the privacy/side-effect statement is separated clearly. Every sentence contributes useful information without repetition.

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?

The description covers what the tool returns, how to use it, and its side-effect-free behavior, which is sufficient given the annotations. It does not describe potential failures or the quarantine behavior in the description itself, but the input schema already documents quarantine for from_docs results.

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?

Input schema coverage is 100%, so both parameters are already documented. The description reinforces the meaning of from_docs and url by mentioning human docs pages and OpenAPI URLs, but it does not add significant new semantic detail beyond the schema.

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 clearly states the tool's purpose: submit an API URL and receive agent-ready tools and artifacts. It names the resource (API spec or docs page) and the action (comprehend), but it does not explicitly contrast itself with the sibling list_surfaces.

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

Usage Guidelines3/5

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

The description explains when to use from_docs for human docs pages instead of OpenAPI URLs, which provides some usage context. However, it never mentions the sibling tool list_surfaces or gives explicit guidance about when to prefer one tool over the other.

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

All surf toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

The two tools have clearly distinct purposes: one enumerates API surfaces already served by the host, while the other ingests an external API's OpenAPI or docs URL and returns agent-ready artifacts. There is no realistic scenario where an agent would struggle to choose between them.

Naming Consistency5/5

Both tools follow the same verb_noun snake_case convention: comprehend_api and list_surfaces. The pattern is consistent, predictable, and each verb accurately describes the tool's action.

Tool Count4/5

Two tools is slightly below the typical 3–15 range, but it is reasonable for the server's narrow purpose of listing existing API surfaces and comprehending external APIs. Each tool is substantial and earns its place, so the low count feels like a deliberate lean scope rather than a deficiency.

Completeness5/5

The tool set covers the full intended workflow: discover what is already served via list_surfaces, and turn any external API into usable agent tools via comprehend_api. Since the server explicitly does not host, register, or persist APIs, no additional management lifecycle tools are needed.

Resources