Get a project's public root index: every resource with record counts and URLs, custom routes, auth mode, and export links (openapi.json, types.ts, postman.json, db.json, GraphQL). No adminKey needed. Try project "demo" for the shared public playground.
| Name | Required | Description | Default |
|---|---|---|---|
| project | Yes | Project id (e.g. demo). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It states it is public (no adminKey needed) and lists return contents. It does not mention side effects, but as a read operation, this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no extraneous information. The first sentence lists all return elements, the second adds auth info and an example. Efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is complete: it explains what is returned, that no authentication is required, and provides an example. No gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter. The description adds context by calling it a 'project id' and providing an example ('demo'), which adds value beyond the schema's bare description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets a project's public root index, listing resources, routes, auth mode, and export links. It uses a specific verb ('Get') and resource ('project's public root index'), distinguishing it from sibling tools like query_records.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description notes that no adminKey is needed, indicating it is a public read operation. It also suggests trying the 'demo' project. While it does not explicitly contrast with alternatives, the context is sufficient for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool maps to a distinct resource/operation: project lifecycle, resource seeding, artifact import, record CRUD, custom routes, snapshots, request inspection, and external API status. Even the data-population tools are clearly separated by existing project (add_resource) versus new project (import_data/create_project).
Most tools follow a clear verb_noun pattern (add_resource, create_project, query_records, write_record, delete_project, etc.). A few noun-style names (custom_route, project_info, snapshots) break the pattern, but all names are snake_case and readable.
Eleven tools is a well-scoped set for a mock API server: project creation/deletion, data population/import, record operations, snapshots, custom routes, inspection, and API status all have dedicated tools without redundancy.
The core workflow is well covered: create/delete projects, add/import resources, CRUD records, snapshot state, define routes, and inspect requests. The main gaps are the lack of explicit resource deletion and custom-route update/delete, but these are workaroundable rather than blocking.