registry_statsHow large this index is, what it holds, how much of it has been verified by introspection, and which upstream registries are federated.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavioral context by specifying what the statistics cover and the concept of introspection verification. No side-effect or return-format disclosure, but annotations cover the safety profile.
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?
A single sentence that packs four distinct aspects of the statistics without redundancy. It is front-loaded with 'How large this index is' and avoids filler.
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 stats tool, the description covers what the operation tells you. There is no output schema, so a structured return format isn't specified, but the listed categories are sufficient for an agent to understand the tool's value. Minor gap: no explicit statement of the output representation.
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 takes zero parameters, so the schema is trivial. Per the baseline for parameterless tools, the description is not required to elaborate parameter semantics.
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 enumerates the exact content of the statistics (size, contents, verification, federated registries), which makes the tool's purpose identifiable. It lacks an explicit action verb like 'return' or 'show', but the title and description together clearly indicate a stats/inspection tool, and it is distinct from the find_* siblings.
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?
The description implies the tool is for retrieving index statistics, but does not state when to use it in preference to find_resource/find_tool, nor any exclusions. The purpose difference is obvious enough that an agent can infer usage, but explicit guidance is absent.
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 has a clearly distinct purpose: find_resource searches for services/capabilities, find_tool searches individual tool schemas, publish_resource registers new resources, and registry_stats reports index health. The descriptions explicitly guide when to use find_resource vs find_tool, eliminating boundary confusion.
Three tools follow a clean verb_noun snake_case pattern (find_resource, find_tool, publish_resource), while registry_stats is a noun_noun exception. The naming is still predictable and readable, but the one non-verb-led tool is a minor deviation.
Four tools is well-scoped for an ARD index: search for resources, search for tools, publish, and inspect stats. Each tool covers a distinct and necessary function without redundancy or bloat.
The index covers the core lifecycle of discovery and publishing well, with search, publish, and stats operations. There is no explicit update or unpublish operation for resources, but the verification-on-publish design mitigates the impact of that gap.