Valet

Call a website's connector

call_site_connector

Destructive

Run one tool on a connector attached to a website and return what the connector answered. It is the sampling step of building a page that calls live data: discover, attach, read the schemas, then call one tool for real before you write any page code.

Call it because a schema is not a shape. list_site_connectors gives you each tool's name and argument schema, which is what your call has to satisfy; this tells you what comes back, which is what the page has to parse. Results are text to read, not JSON to assume: many servers answer in markdown tables or prose, some expose a single meta-tool taking a whole command as one string, and a server that completes the handshake can still refuse half its tools when the stored credential's scope does not cover them. One real call settles all three.

This runs the tool for real, with the organization's own credential and whatever side effects the tool has. It is not a dry run and there is no preview: a tool that sends, writes, or deletes will do so. Prefer a read-only tool when you are only learning the shape, and ask the user before running anything that changes their systems.

The connector must already be attached to the site — attach_site_connector does that — and must be an HTTP MCP server. A tool that answers with an error is reported as an error carrying the connector's own text, which is usually the sentence that says what to fix. Requires connecting a Valet account.

Input Schema

TableJSON Schema

Name	Required	Description
`args`	No	Arguments for the tool, as an object matching the tool's own input schema from list_site_connectors. Omit it for a tool that takes none.
`site`	Yes	Required. The site's name.
`tool`	Yes	Required. The tool to run, spelled exactly as list_site_connectors reports it.
`org_name`	No	The Valet organization the site belongs to. Omit to use the organization the account joined first.
`connector`	Yes	Required. The name the connector is attached under, which is the name a page calls it by.

TDQS

A4.6/5.0

Behavior5/5

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

The description discloses critical behavioral traits beyond annotations: it is not a dry run, side effects are real, error handling carries the connector's text, and results are text not JSON. It also mentions credential usage and preconditions (connector attached, HTTP MCP server, Valet account). This adds significant value beyond the destructiveHint=true and readOnlyHint=false annotations, with no contradictions.

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 well-structured with front-loaded main action, logical flow, and separate paragraphs for different aspects. It is slightly long but every sentence adds value, covering purpose, usage guidance, behavioral notes, and prerequisites. It could be trimmed by a sentence or two, but the length is justified by the complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (5 params, destructive side effects, no output schema), the description is remarkably complete. It covers preconditions, side effects, error handling, response format (text), and credential requirements. It explains the workflow context (sampling step) and when to use alternatives. No gaps remain for an agent to misuse the tool.

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?

The input schema has 100% description coverage, so the baseline is 3. The description adds little new parameter-specific meaning beyond what the schema already provides (e.g., 'args' should match the tool's schema from list_site_connectors, 'connector' is the name attached under). While helpful, this is marginal improvement over the schema descriptions.

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 explicitly states the tool's purpose: 'Run one tool on a connector attached to a website and return what the connector answered.' It also distinguishes itself from sibling tools like list_site_connectors (which gives names and schemas) and attach_site_connector (which attaches the connector), making the unique role clear.

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

Usage Guidelines5/5

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

The description provides clear guidance on when to use this tool: after 'discover, attach, read the schemas' and because 'a schema is not a shape' – this tool reveals the actual response shape. It explicitly contrasts with list_site_connectors and advises to 'prefer a read-only tool when you are only learning the shape' and to 'ask the user before running anything that changes their systems.' The prerequisites (connector attached, HTTP MCP server, Valet account) are also stated.

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

All Valet tools Inspect

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

A4.3/5.0

Disambiguation5/5

Every tool pairs a distinct resource with one action: site, connector, catalog, design system, access, and sharing are separate concerns. The four list_* tools are clearly differentiated by object (sites, site connectors, attachable connectors, catalog connectors), and attach/detach, publish/rename/delete, and set/share are unambiguous.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern with no stray camelCase or inconsistent verb styles. The naming is predictable: list_X for discovery, get_X for single reads, create_/delete_/rename_/attach_/etach_ for lifecycle actions, and set_/ share_/ call_ for specific operations.

Tool Count4/5

At 16 tools the server is slightly over the ideal 3-15 range, but each tool addresses a distinct part of the site-publishing and connector-attachment workflow. None feel redundant, and the set remains navigable despite being a bit dense.

Completeness4/5

The site lifecycle is essentially complete: publish, read, list, rename, set access, share, and delete, with updates supported through republishing. The connector lifecycle covers discovery, creation, attachment, listing, calling, and detach, but there is no connector update/delete or share-revocation tool, which are minor gaps agents can work around.

Resources

Need Help?