Enable or update sharing for a verification you own. access_type is 'anyone_with_link' (public URL) or 'restricted' (only invited emails). Optionally pass invite_emails to grant access. Returns the share URL and invited emails. Anonymous verifications can't be shared.
| Name | Required | Description | Default |
|---|---|---|---|
| access_type | Yes | ||
| invite_emails | No | ||
| verification_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses mutation, ownership requirement, access_type behavior, optional invite_emails, return value, and the anonymous restriction. It doesn't detail error cases or whether existing invite emails get replaced, but the core behavior is well-covered.
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?
Three sentences effectively front-load the purpose, then cover parameter semantics and a critical restriction. There is no wasted wording or redundancy.
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 3-param tool with an output schema, the description covers purpose, all parameter semantics, output behavior, an ownership precondition, and an edge-case restriction. No significant 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 0%, and the description fully compensates by explaining all three parameters: verification_id via 'a verification you own,' access_type with its two allowed values described, and invite_emails as optional for granting access. This adds meaning beyond the bare schema types.
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 opens with 'Enable or update sharing for a verification you own,' which is a specific verb+resource combination. It clearly differentiates from sibling tools like get_verification_share and unshare_verification by framing this as creating or updating sharing.
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?
Clear context is provided: use this tool to enable or update sharing for owned verifications, with the explicit exclusion that anonymous verifications can't be shared. It doesn't explicitly name alternatives like get_verification_share or unshare_verification, but the operation scope is unambiguous.
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 targets a distinct action and resource: uploads, account usage, listings, verifications, sharing, and the two verification methods are clearly differentiated by input type (single image vs RAW+JPEG). The get_verification and get_verification_share pair is unambiguous due to specific descriptions.
All tool names use lowercase snake_case with a verb_noun pattern (create, get, list, share, unshare, verify), making the set predictable and consistent. Even longer names like verify_content_credentials follow the same verb-first convention.
With 11 tools, the server covers uploads, verification, results retrieval, sharing, account usage, and marketplace listing retrieval without redundancy. This is a well-scoped count for the feature set.
The verification lifecycle is well covered: create (two methods), upload, get, list, share/unshare, and usage check. The only notable gap is that marketplace listing management is read-only (no create/update/delete), but that's tangential to the core verification purpose.
