Export a JSON TrustOps policy for one MCP server with allow, blocked tools, required scopes, freshness, and approval gates.
| Name | Required | Description | Default |
|---|---|---|---|
| client | No | ||
| max_risk | No | ||
| identifier | Yes | Canonical server identifier in namespace/name format. | |
| requires_oauth | No | ||
| max_freshness_hours | No | ||
| no_write_without_approval | 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 declare readOnlyHint=true, and the description is consistent with a read-only export. It adds useful context about the return format (JSON) and the specific contents of the policy, which goes beyond the annotation.
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, well-structured sentence that starts with the verb and quickly conveys the core purpose and contents. No filler or 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?
For a tool with 6 parameters and no output schema, the description provides a solid overview but lacks detailed parameter semantics and return structure. It is adequate but leaves gaps about how to configure the policy and what the JSON response looks like.
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 only 17% (identifier only). The description vaguely references policy features like 'allow, blocked tools, required scopes, freshness, and approval gates' but does not map them to specific parameters (client, max_risk, requires_oauth, max_freshness_hours, no_write_without_approval). It fails to compensate for the low schema coverage.
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 'Export' with a clear resource ('JSON TrustOps policy for one MCP server') and enumerates the policy components. It distinguishes itself from sibling tools like create_mandate (creation vs export) and get_server_report (report vs policy).
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?
No guidance is provided on when to use this tool versus alternatives. It does not mention when to choose export_policy over create_mandate or other policy-related tools, offering no exclusions or preferred contexts.
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 resources and actions (e.g., get_agent vs. get_drift_report). A few pairs like search/search_servers and fetch/get_server_report overlap in intent, but descriptions clarify differences in output and purpose. Agents may need to read carefully but can generally tell tools apart.
Nearly all tool names follow a verb_noun snake_case pattern (list_agents, create_mandate, export_policy). The bare aliases 'fetch' and 'search' deviate slightly, but are clearly intentional, and there is no mix of camelCase or other styles. Overall consistent and predictable.
22 tools is on the heavy side, falling into the '16-25' borderline range. While each tool appears to serve a distinct function, the set could be consolidated (e.g., the multiple 'get_*_options' tools). It is not excessive enough to be chaotic, but it is above the ideal 3-15 range.
The tool surface covers core workflows for server search, comparison, report generation, policy export, mandate creation, agent risk management, and decision-making. Minor gaps exist, such as no create/update/delete for most resources and no subscription creation, but the domain is read/decision-heavy and core lifecycle coverage is adequate.