Create a durable agent session with scoped permissions (persisted to DATA_DIR). Non-custodial.
| Name | Required | Description | Default |
|---|---|---|---|
| owner | Yes | ||
| ttlHours | No | ||
| sessionKey | No | ||
| permissions | No | ||
| maxNotionalUsd | No | ||
| allowlistSymbols | No | ||
| maxDailyNotionalUsd | 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?
Discloses persistence to DATA_DIR and non-custodial nature, which are beyond the schema. But with no annotations, it should describe side effects (e.g., overwrite behavior, auth needs) and doesn't. Adequate but not thorough.
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?
Two sentences, front-loaded with action and object. No redundant or filler text. Highly efficient given the needed information.
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?
With 7 parameters, no annotations, no output schema, the description covers very little. Missing: return value, parameter relationships, error conditions, and usage examples. Incomplete for an agent to use correctly.
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 description must explain parameters. It mentions 'scoped permissions' but gives no details on any of the 7 parameters (owner, ttlHours, sessionKey, permissions, etc.). Completely insufficient.
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?
Clearly states it creates a durable agent session with scoped permissions and non-custodial nature. Distinguishes from sibling session tools (kill, list, update) by specifying creation. Lacks full specificity on 'durable'.
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 on when to use this tool versus alternatives. Does not mention prerequisites, context, or excluded scenarios. Only describes what it does, not when to use it.
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 have clearly distinct purposes, but some pairs (e.g., stocktoken_quote vs stocktoken_simulate, stocktoken_protocols vs stocktoken_find_pools) could cause confusion if descriptions are not read carefully.
All tools share the 'stocktoken_' prefix, but the pattern is inconsistent: some use verb_noun (access_activate, execute_plan), others use single verb (get, list, simulate), and some use noun phrases (metrics, liquidity_matrix, morpho_deposit_plan).
37 tools is high for an MCP server, covering access, subscriptions, sessions, tips, and trading. While many are needed for a full on-chain system, the count feels excessive and could be streamlined.
The server covers most major operations: listing, pricing, quoting, simulation, execution planning, liquidity, access control, and system management. Minor gaps exist (e.g., no broadcast tool, no explicit cancel/undo), but overall it's comprehensive.