Pane

Manage App Connections

connections

Destructive

A v2 app's Connections: the stored credential (a static header token, or a full generic OAuth2 client) a manifest webhook rule authenticates its delivery target with, bound to a host so the credential can never be exfiltrated to another one. There is no update action: change a connection by deleting and recreating it. Actions: create stores a static or oauth2 connection and returns its metadata, never the secret; list returns the app's connections as metadata plus a non-reversible fingerprint, never any secret; delete is idempotent; consent_url builds (never fetches) the browser URL that completes an oauth2 connection's consent, since that is inherently a human-in-a-browser step an agent key cannot complete. A newly created oauth2 connection starts in pending_auth until the owner opens the consent_url and approves.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No	create only. Defaults to `static`.
`name`	No	create / delete / consent_url. The connection name (lowercase, starting alphanumeric, up to 64 chars) that a manifest webhook rule's `connection` field references.
`label`	No	create only. Optional owner-facing label.
`action`	Yes	create: store a webhook connection, a stored credential (static header token or a full generic OAuth2 client) a manifest webhook rule authenticates its target with (app_id+name+allowed_host, plus kind-specific fields). list: the app's connections as metadata plus a non-reversible fingerprint, never any secret (app_id). delete: idempotent (app_id+name). consent_url: build (never fetch) the browser URL that completes an oauth2 connection's owner consent (app_id+name); hand it to the signed-in owner to open, since an agent key cannot complete OAuth consent itself.
`app_id`	Yes	The app id.
`scopes`	No	create only (oauth2). Space-delimited scopes for the authorize request.
`provider`	No	create only. Freeform display label only, e.g. "hubspot"; not validated against any allowlist.
`client_id`	No	create only, required for kind=oauth2. Your OAuth2 app's client id.
`auth_params`	No	create only (oauth2). Extra key/values merged into the authorize redirect (e.g. to request offline access).
`auth_scheme`	No	create only (oauth2). The scheme the access token is sent under. Defaults to "Bearer"; set e.g. "Zoho-oauthtoken" for a non-Bearer provider.
`header_name`	No	create only (static). The header the credential rides in. Defaults to "Authorization".
`allowed_host`	No	create only, required for both kinds. The host-binding exfiltration defence: an exact DNS host ("api.hubapi.com") or a single leftmost wildcard ("*.zohoapis.com"). The stored credential is attached to a delivery only when its url host matches; a rule later repointed elsewhere fails delivery rather than sending the secret to the wrong host.
`header_value`	No	create only, required for kind=static. The header value to send, e.g. "Bearer sk_live_...". Encrypted at rest and never returned by any call.
`token_params`	No	create only (oauth2). Extra key/values merged into the token POST.
`authorize_url`	No	create only, required for kind=oauth2. The provider's OAuth2 authorize endpoint (https; rejected if it resolves to a private/loopback/metadata address).
`client_secret`	No	create only, required for kind=oauth2. Your OAuth2 app's client secret. Encrypted at rest and never returned by any call.
`instance_field`	No	create only (oauth2). The name of a token-response JSON field holding the API base URL (e.g. "instance_url"). When set, the relay re-binds allowed_host to that host after consent and resolves relative rule urls against it.
`token_endpoint`	No	create only, required for kind=oauth2. The provider's OAuth2 token endpoint (same https + SSRF rules as authorize_url).

TDQS

A4.3/5.0

Behavior5/5

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

Beyond the annotations (destructiveHint, readOnlyHint), the description reveals critical behavioral traits: never returns secrets, create returns metadata only, delete is idempotent, consent_url builds rather than fetches, and new OAuth2 connections start in pending_auth until owner approval. This adds substantial contextual value not present in annotations.

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 two dense paragraphs with a clear structure: first defines the resource, then elaborates actions and lifecycle. Every sentence contributes meaning (security, idempotency, consent flow), and the length is justified for an 18-parameter tool. It is front-loaded with the core concept.

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?

Despite no output schema, the description explains return behavior for create/list (metadata, fingerprint, never secret), consent_url (returns URL), and the pending_auth lifecycle. It does not cover error cases or pagination, but for a complex tool with thorough schema descriptions, it is largely complete.

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?

Schema description coverage is 100%, and each parameter already has detailed descriptions. The tool description adds high-level context (e.g., allowed_host as exfiltration defense, kind-specific fields) but does not materially alter or augment the per-parameter semantics beyond what the schema provides. Baseline 3 is appropriate.

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 precisely defines the resource—'a v2 app's Connections: the stored credential... bound to a host'—and enumerates the actions (create, list, delete, consent_url) with operational specifics. It clearly distinguishes this from sibling tools by emphasizing host-binding and secret-exfiltration defense, which is unique to this tool.

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 gives explicit usage guidance: 'There is no update action: change a connection by deleting and recreating it' and explains when consent_url is appropriate ('a human-in-a-browser step an agent key cannot complete'). It does not directly name alternative tools but provides clear contextual and exclusionary guidance.

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

All Pane 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

A4.4/5.0

Disambiguation5/5

Each tool targets a distinct resource or action: row operations (get/list/upsert/update/delete/restore) are clearly separated, while apps, attachments, community, grants, ingest, members, publisher, review, and taste each cover a different domain. Even closely related actions like share_link_rotate and domain_set have clearly scoped descriptions, so an agent can reliably select the right tool.

Naming Consistency4/5

Tool names use two patterns: noun-like names for resource areas (apps, attachments, community, grants, ingest, members) and verb_noun names for row operations (upsert_row, delete_row, etc.). This deviation is predictable and readable, but it is not perfectly uniform, so a slight deduction applies.

Tool Count4/5

With 22 tools, the server is on the heavier side, but the breadth of the platform (app lifecycle, data storage, attachments, community, reviews, feedback, identity) justifies the count. Each tool represents a meaningful feature area with multiple internal actions, so none feels redundant.

Completeness5/5

The tool surface covers the full lifecycle for apps (create, read, update, delete), rows (create, read, update, delete, restore, list deleted), attachments, membership, grants, ingest, community, and reviews. Obvious gaps like rollback or version history are not core to the domain, and the presence of get_skill helps agents understand the workflow.

Resources

Need Help?