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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral burden. It explicitly declares 'Free read' signaling a side-effect-free operation, and adds a meaningful guarantee: 'Estimates and observations stay distinct.' This goes beyond a simple read-only label and clarifies data handling. However, it does not mention any potential limitations like data freshness or computational cost, so it's not a 5.
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 with a colon-led list, front-loading 'Free read' for immediate clarity. While the list is long, each item adds specific content scope. It's efficient and well-structured, though slightly dense.
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?
An output schema exists, covering return structure, so the description needn't explain return values. It does provide a comprehensive list of report contents and a behavioral guarantee. However, it omits any mention of the 'limit' parameter and doesn't explain how the report relates to sibling tools like route_task or record_route_outcome, making it less complete for an agent deciding when to invoke it.
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?
The input schema has one parameter 'limit' with a default value but no description. Schema description coverage is 0%, so the description should compensate, but it never mentions 'limit' or how it affects the report. The parameter's meaning is left entirely to inference from its name and type, which is 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?
The description uses a specific verb 'Free read' followed by a detailed resource list: decision/outcome receipts, route modes, compute avoided, predicted savings, predicted-vs-observed cost/latency/energy coverage, and Landauer-floor context. This clearly distinguishes it from sibling tools like get_ledger or list_agents by specifying exactly what efficiency metrics are reported.
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 explicit guidance on when to use this tool versus siblings. It doesn't state 'use this to retrieve efficiency metrics' or mention alternatives like get_ledger for raw data. The usage is only implied by the name and description, but the description lacks direct when-to-use/when-not-to-use instructions.
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 describe_agent and get_agent both return agent information, and best_next_steps vs route_task could be confused in decision-making contexts. The descriptions help clarify, so the ambiguity is limited.
The vast majority of tools follow a verb_noun snake_case pattern (e.g., create_agent, list_agents), but best_next_steps breaks the pattern and compute_efficiency_report reads as a noun phrase. These are minor deviations from an otherwise consistent style.
With 14 tools, the server sits comfortably within the ideal 3-15 range. Each tool serves a specific function in the agent lifecycle or compute-routing workflow, so the count feels well-scoped without unnecessary bloat.
The agent lifecycle is well covered with create, delete, get, list, describe, export/import, evaluation, and ledger access. The compute side includes profile registration, task routing, outcome recording, and reporting. Minor gaps like no direct agent update or profile listing exist, but they are workable.