Ask FLOCORE's MEMORY: 'what do I know about X?'. Hybrid-lite retrieval over the semantic world-model; every result is PROVENANCE-STAMPED (who / source / trust). Read-only, silo-scoped.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| scope | No |
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?
With no annotations, the description carries the full disclosure burden. It explicitly states read-only, silo-scoped, and provenance-stamped outputs with who/source/trust, which are meaningful behavioral traits. It doesn't detail edge cases, rate limits, or failure modes, but the core side-effect and result characteristics are disclosed.
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, front-loaded with the query template, and each sentence adds information about behavior or result format. The only minor issue is unexplained jargon ('hybrid-lite', 'silo-scoped') packed into a compact phrase.
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 read-only retrieval tool with one required parameter, the description covers the core purpose and result traits, making basic invocation possible. However, with no output schema and no parameter descriptions for limit/scope, it is not fully self-sufficient for all call variations.
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?
Schema description coverage is 0%, so the description must explain the three parameters. It hints at the query parameter through the 'what do I know about X' template, but it never explains limit or scope, nor how 'silo-scoped' maps to the scope parameter. This is a meaningful gap.
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 clearly identifies a retrieval action over FLOCORE's memory/world-model, with a concrete query template ('what do I know about X?'). It also adds read-only and silo-scoped qualifiers that separate it from the ticket/tenant/queue siblings, though 'hybrid-lite' is jargon that slightly obscures the exact mechanism.
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 'ask what do I know about X' template implies when to use it, but there is no explicit when-not-to-use guidance or comparison with alternatives like flocore_ontology_entities. A capable agent can infer the use case, but it is left to implication rather than stated.
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 domains, but flocore_mesh_lanes and flocore_orch_board both expose mesh lane liveness, and flocore_list_tickets overlaps with flocore_queue_summary in surfacing work items by status. The descriptions help clarify the difference, but an agent could still hesitate when selecting between them.
All tools share the flocore_ prefix and use snake_case, which is good, but the pattern is inconsistent: some use verb_noun (create_ticket, list_tenants, list_tickets) while others are bare noun phrases (mesh_lanes, ontology_entities, orch_board, queue_summary) or a bare verb (recall). The convention is readable but not uniform.
Eight tools is a well-scoped size for a governed operational server. Each tool represents a meaningful capability, and there is no obvious bloat or overly thin coverage.
The read side is strong: tenants, tickets, mesh state, ontology, orchestration board, queue summary, and memory recall are all covered. However, the ticket lifecycle is incomplete with only create and list, lacking update, resolve, or single-ticket detail operations, which creates a notable gap for operational workflows.