linksInventory of every owned link, one record each: residency, protection state, and published-artifact detail. Use this to see what is currently published, or to find a label to act on. Live-tunnel capacity and usage totals come along as context. For plan, entitlement and quota headroom, use account_status instead. Owned links are unlimited by count.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds useful context beyond that: the inventory scope, included context fields (live-tunnel capacity and usage totals), and the unlimited-count property. No contradictions with annotations.
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?
Four dense sentences, each earning its place: what the inventory contains, when to use it, when to use the alternative, and a relevant count constraint. The core purpose is front-loaded.
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 parameterless read-only list tool, the description fully covers what the agent gets, when to call it, and what not to use it for. It even describes the record contents sufficiently in lieu of an output schema.
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?
The tool has zero parameters and schema coverage is 100%, so the baseline is 4. The description adds no parameter details, but none are needed.
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?
States a specific verb and resource: an inventory of every owned link with per-record fields (residency, protection state, published-artifact detail). It is clearly distinguishable from siblings like account_status, protect_link, and revoke_link.
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?
Explicitly says when to use it ('to see what is currently published, or to find a label to act on') and names the alternative for related but different needs ('For plan, entitlement and quota headroom, use account_status instead').
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.
Most tools target distinct actions: account_status is account-level, links is inventory, serve/stop_remote are publish/unpublish, and the protection tools form a clear lifecycle. The only possible confusion is revoke_link versus unprotect_link, since both invalidate access in different ways, but the descriptions distinguish them well.
The link-mutation tools follow a consistent verb_noun pattern: protect_link, renew_link, revoke_link, unprotect_link. However, account_status and links are noun-only, serve is a bare verb, and stop_remote uses an inconsistent object, so the naming conventions are mixed.
Eight tools is well-scoped for this server's purpose: account awareness, link inventory, publishing, unpublishing, and protection management. Each tool serves a distinct function and none feel redundant.
The core lifecycle is covered: publish via serve, unpublish via stop_remote, inventory via links, and full protection management via protect/renew/revoke/unprotect. Minor gaps exist such as no explicit update-to-existing-link operation, but agents can likely work around these.