get_capability_graphReturn a Capability Graph snapshot (nodes, shared-capability edges, capability index) for agent planning.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| min_similarity | 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?
Annotations already cover the read-only, idempotent, non-destructive nature. The description adds value by specifying the output composition (nodes, edges, capability index) and characterizing the result as a snapshot, giving the agent a clearer model of what invoking the tool returns. No contradiction 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?
The description is a single sentence that is front-loaded with the core action and resource. Every element—snapshot, node/edge/index contents, and planning purpose—adds useful information without redundancy.
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?
The tool has no output schema, so the description is the only source for return-value expectations; it provides a useful high-level breakdown. However, it does not explain how the optional parameters shape results or when this graph should be chosen over sibling capability tools, leaving moderate gaps for an autonomous agent.
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% and the description does not mention limit or min_similarity at all. The agent must infer their meaning from parameter names and constraints, with no added explanation of how they affect the returned graph.
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 ('Return') and names a precise resource ('Capability Graph snapshot'), including its contents (nodes, shared-capability edges, capability index). It also states the intended use case ('for agent planning'), which distinguishes it from sibling tools like list_capabilities and search_tools.
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 phrase 'for agent planning' gives a clear context for when the tool is useful. However, it does not explicitly state when to avoid it or name alternative tools for capability listing/searching, so it lacks explicit exclusions.
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 mostly distinct with clear descriptions. Potential overlap exists among search_tools, recommend_tools, list_capabilities, and get_capability_graph, but each serves a different purpose (query vs. recommendation vs. high-level list vs. relational graph). inspect_tool_server vs. get_tool (server vs. tool) and verify_web vs. understand_webpage (reachability vs. content) are clearly separated. Minor ambiguity between list_capabilities and get_capability_graph, but descriptions clarify.
All tool names follow a consistent verb_noun pattern (e.g., compare_tools, get_tool, search_tools, verify_web). No mixing of camelCase or inconsistent styles. The naming is uniform and predictable.
12 tools is within the ideal 3-15 range and appropriate for a directory service that provides search, retrieval, comparison, recommendation, inspection, invocation, and web verification. The count is comprehensive without being overwhelming, and each tool adds distinct value.
The tool set covers core directory operations (search, get, compare, recommend) and additional utilities (inspect, invoke, trust score, capability graph). It lacks a direct 'list all tools' or 'list all servers' endpoint, but search_tools and list_capabilities can approximate this. The inclusion of web verification and understanding tools extends beyond the catalog domain, but they are useful adjuncts. Overall, the surface is well-rounded with minor gaps.