Ask the corpus what it covers on a given topic. Returns the topical map with citations, or uncited(out_of_scope) when the topic is not covered. Optional repo scopes the question to one repo (Phase 3.5). Returns: The scope of the requested corpus region. Example: call introspection_corpus_probe_scope with arguments {}.
| Name | Required | Description | Default |
|---|---|---|---|
| repo | No | ||
| topic | Yes |
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 mark this as read-only/non-destructive. The description adds useful behavioral details: the out_of_scope return and the optional repo scoping. No contradiction with annotations exists.
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?
The description is short and front-loaded, but the 'Returns: The scope of the requested corpus region' sentence is redundant with the earlier output statement. The example 'with arguments {}' is misleading because the schema requires a 'topic' argument.
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 two-parameter tool, the description covers the main return modes and optional scoping. It lacks explicit interaction with sibling introspection tools, but the basic invocation context is adequately complete.
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?
With 0% schema description coverage, the description must compensate, and it only partially does: it explains 'repo' as scoping to one repo and implies 'topic' is the subject of the probe. It does not clarify topic format, required behavior, or relationship between the two parameters beyond that.
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 action ('Ask the corpus what it covers') and resource ('corpus') and clarifies the output ('topical map with citations' or 'out_of_scope'). It does not explicitly name sibling tools, but the scope/coverage framing distinguishes it from query/generate/probe_disagreement.
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?
It clearly implies when to use: to determine corpus coverage on a topic. It also explains the optional repo scoping behavior. However, it gives no explicit exclusions or comparison to alternative introspection 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.
Tools are grouped by clear domain prefixes (federation_*, introspection_*, moltbook_*) with each targeting a distinct resource+action (bond_post/release/status, key_challenge/bind/status, journal_append/read). The primary near-overlap — catalog_search_multi vs catalog_search_grouped_multi — is explicitly disambiguated in descriptions. Minor confusion risk exists among the four knowledge tools (federation_help, federation_why, about_us_about, how_to_about) but their purposes (how/why/manual/walkthrough) are distinct enough.
The dominant `federation_<verb>_<noun>` pattern (create_tenant, list_agents, bond_release) is strong, but it's mixed with bare-noun tools (federation_arena, federation_offer, federation_solvency, federation_pricesheet, federation_help) and noun-noun variants (federation_manager_tree, federation_tenant_info). Non-federation tools use a loose `<domain>_<verb>` or single-token convention (legal_get, web_research, about_us_about). Readable overall, but conventions are noticeably mixed across the surface.
At 72 tools this crosses the 50+ threshold for an extreme count. While the federation's scope is genuinely broad (manager lifecycle, tenants, catalog, agents, bonds, keys, journal, canon, introspection, social, email, research), the surface is bloated — roughly 15 bare introspection tools (list_nodes, probe, confidence, diff, coverage_gaps, co_decisions, climb_history, change_graph, change_reach, corpus_*) cover meta-self-knowledge that could plausibly collapse into fewer verbs. Agents would face a very large selection space.
The tool surface is exhaustively complete for the federation domain: applicant and operator sides of admittance, full manager lifecycle (create/list/freeze/attest/bond/key), full tenant lifecycle (create/list/info/update/suspend/delete/enter), catalog discovery with change-detection, pricing, solvency, latency, journaling, governance, legal, and even external outreach (email/moltbook/research). No dead ends exist — every write has a corresponding read/status path, and branched platform tools are intentionally deferred behind enter_tenant rather than omitted.