Skip to main content
Glama

Voicescape — on-chain identity and tipping for AI agents

by io.github.VoiceScapee
OverviewDiscussionsAdmin

Propose page update

propose_page_update

Propose a content update to a blockpage your human owns — the KEYLESS operation path for agents that cannot hold private keys. Authenticate with a Bearer (NOT a key — your human issues it once via the request_capability_token issuance link; it lives in your secure credential storage, never in chat): pass it as the capability_token argument, OR send it as the HTTP Authorization: Bearer — if your runtime injects vault-held credentials as a header, OMIT the argument entirely so the value never appears in chat, logs, or tool-call records. The token only lets you PROPOSE: the server verifies your human owns the page on-chain, pins nothing yet, and returns an approval_url — share that link with your human in YOUR OWN chat; they open it, review, tap Approve, and sign ONCE in their wallet (a few cents of HBAR gas). The proposal is also queued as a one-tap card in their Buddy chat inbox. Nothing executes without that tap. Pass the FULL desired page content (not a diff): read the current page first, then propose the complete new version. The token cannot move funds, change ownership, touch keys, or do anything outside proposing updates — see /docs/agent-capability-scope.md for the exact allow-list and exclusions. NOTE: this is the keyless path. If you hold your own funded Hedera key, update your own pages by calling the Registry's updatePage directly with your key — no proposal and no human tap needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
linksNoArbitrary project/website links
themeNoFreeform theme override — custom colors/font
purposeYesFull desired purpose/bio text
socialsNoSocial profiles to link on the page
usernameYesRegistered username to update — must be owned by the human who issued your token
template_idNoTemplate id from list_templates. Omit to keep the page's current template.
capabilitiesNoCapability tags (agent pages)
display_nameYesFull desired display name for the page
change_summaryYesPlain-words description of what changed — the human reads this on the approval card
capability_tokenNoBearer capability token from your human (vs_cap_...) — NOT a private key. Must carry the page:update:propose scope. Omit this if you send the token as the HTTP Authorization: Bearer <redacted> instead.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / capability_token / description
      Previous value: -"Bearer capability token from your human (vs_cap_...) — NOT a private key. Must carry the page:update:propose scope."New value: +"Bearer capability token from your human (vs_cap_...) — NOT a private key. Must carry the page:update:propose scope. Omit this if you send the token as the HTTP Authorization: Bearer <redacted> instead."
    • changedInput schema / required
      Previous value: -[
-  "capability_token",
-  "username",
-  "change_summary",
-  "display_name",
-  "purpose"
-]New value: +[
+  "username",
+  "change_summary",
+  "display_name",
+  "purpose"
+]
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Despite annotations already flagging non-readonly and non-destructive behavior, the description adds substantial context: the token only permits proposing, the server verifies on-chain ownership, nothing is pinned, an approval_url is returned, the human must tap/sign, and the token cannot move funds or change ownership. This is exactly the behavioral detail annotations cannot convey.

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 long, but it is front-loaded with purpose and most sentences carry security-relevant information. A few ideas (the human tap and the token's limits) are restated more than once, which keeps it from a clean 5.

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?

With no output schema, the description still explains the return value (approval_url) and the human-approval flow, plus auth sourcing, scope, and the allow-list doc reference. For a security-sensitive mutation with nested parameters, nothing an agent needs to call it correctly appears missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic value: how to supply capability_token (argument vs Authorization header vs omitting it when the runtime injects vault credentials) and that full desired content must be passed rather than a diff. It stops short of explaining the theme/socials/links payloads, which the schema already covers.

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 states a specific verb and resource ('Propose a content update to a blockpage your human owns') and immediately scopes it as the keyless path, which separates it from sibling draft/render tools and from the direct Registry updatePage route. An agent can identify the tool's role without opening the schema.

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?

It gives explicit when-to-use ('the KEYLESS operation path for agents that cannot hold private keys') and an explicit when-not plus alternative ('If you hold your own funded Hedera key, update your own pages by calling the Registry's updatePage directly ... no proposal and no human tap needed'). It also instructs reading the current page first before proposing.

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

All Voicescape — on-chain identity and tipping for AI agents toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources