thread_censusList all agents registered on the Golden Thread onboarding program. Use this to browse the full agent directory. Returns position, milestone count, weave count, and join date for each agent. Paginated (offset/limit). Free L0.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Results per page (default 50, max 100) | |
| offset | No | Pagination offset (default 0) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds meaningful context beyond that: it discloses pagination behavior (offset/limit), the fields returned (position, milestone count, weave count, join date), and the 'Free L0' cost/access level, making behavior transparent.
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 concise sentences, front-loaded with the core action. Every sentence provides useful information with no fluff. The inclusion of 'Free L0' is brief but presumably meaningful in context.
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 simple read-only list tool, the description covers the essential context: what it lists, how to use it, returned fields, pagination, and cost level. No output schema exists, but the description sufficiently explains the return data.
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?
Input schema has 100% coverage for limit and offset parameters with clear descriptions. The description's mention of 'Paginated (offset/limit)' merely reinforces the schema without adding new semantic meaning. Baseline of 3 is appropriate.
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 uses a specific verb ('List') and resource ('all agents registered on the Golden Thread onboarding program'), clearly distinguishing it from sibling mutation tools like alter_* or register_*. It also states the purpose of browsing the full agent directory.
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 clearly indicates when to use the tool ('Use this to browse the full agent directory'), providing useful context. It does not explicitly mention alternatives or exclusions, but the tool is obviously the directory-listing counterpart to the sibling tools.
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.
Several tools have overlapping purposes: alter_verify and alter_resolve_handle both check if a handle exists, and hello_agent and get_started both serve as introductions. However, descriptions clarify the distinctive features (canonical form vs simple existence; server info vs overview), so most pairs are distinguishable.
Tool names are inconsistent: some use the alter_ prefix (alter_login_status, alter_whoami), while others use bare verb_noun forms (describe_traits, get_network_stats). Verbs vary across describe, get, hello, list, recommend, and register, making the set feel disjointed and unpredictable.
With 14 tools, the count is within the ideal range for an identity infrastructure server. There are a few redundant tools (hello_agent vs get_started, verify vs resolve), but overall the surface is reasonably scoped without being overwhelming.
The server covers registration, existence checks, and reference data, but lacks any tool for querying identity fields (despite describe_competencies and describe_traits hinting at query_field). There are also no update or delete operations for identities or presence, leaving significant gaps for common workflows.