Free read: decision/outcome receipts, route modes, compute avoided, predicted savings, predicted-vs-observed cost/latency/energy coverage, and Landauer-floor context. Estimates and observations stay distinct.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | 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?
With no annotations provided, the description carries the full behavioral burden. 'Free read' explicitly communicates no side effects, and 'Estimates and observations stay distinct' discloses an important data-handling guarantee. It does not mention pagination or authorization, but for a read-only report with an output schema, this is reasonably transparent.
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 dense sentence with no filler. It front-loads the read-only status and then lists concrete content areas. The phrasing is compact and every phrase adds meaning, though 'Landauer-floor context' is somewhat jargon-heavy.
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 one optional parameter and an output schema, the description covers the core subject matter and read-only nature. However, it omits when-to-use guidance and does not explain how limit affects the report or how this tool relates to get_ledger, leaving meaningful gaps for an agent deciding which tool to invoke.
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 never mentions the only parameter, limit. The schema's title and default value provide minimal meaning, but the description adds no detail about pagination, result caps, or how the limit affects the report, so it fails to compensate for the lack of schema descriptions.
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 read-only reporting tool and enumerates specific content areas: decision/outcome receipts, route modes, compute avoided, predicted savings, predicted-vs-observed coverage, and Landauer-floor context. It is more specific than a generic phrase, but it does not explicitly contrast with siblings like get_ledger or record_route_outcome.
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?
There is no guidance on when to use this tool versus alternatives such as get_ledger or best_next_steps. 'Free read' implies safe usage, but the description does not state the conditions that should lead an agent to choose this report over other 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.
Each tool targets a distinct resource and action: agent lifecycle tools are clearly separated from ledger/report tools, and routing tools split cleanly into profile registration, task routing, outcome recording, and reporting. Even the two 'routing' tools differ meaningfully—best_next_steps recommends graph-neighbor cognitive moves while route_task selects a least-burden compute route.
Most tools follow a clear verb_noun pattern (create_agent, delete_agent, export_state, record_route_outcome, register_compute_profile, route_task). Minor deviations exist, such as best_next_steps being a noun phrase rather than a verb-prefixed command, but the overall convention is predictable and readable.
Fourteen tools is well within the ideal range and each tool earns its place: agent lifecycle management, state transfer, ledger access, evaluation, and the routing/profile/outcome workflow all have dedicated operations. The count feels proportionate to the server's dual focus on developmental agents and compute routing.
The agent lifecycle is well covered with create, read, update-via-evaluation, delete, list, export, and import, and evaluation produces ledger events. The main gap is compute-profile management: profiles can be registered but not listed, updated, or removed, and graph node/edge mutations are only indirect through submit_evaluation.