list_first_party_measurementsRetourne uniquement les bancs publics datés OutilsIA (machine, runtime, tok/s, référence). Une mesure n'est jamais extrapolée à un autre PC. Campagne multi-machines non terminée.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No |
| Name | Required | Description | Default |
|---|---|---|---|
| measurements | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, establishing safe read behavior. The description adds significant context: the tool returns only first-party, dated, non-extrapolated measurements from an unfinished multi-machine campaign. This goes beyond annotations to inform the agent about data scope and limitations.
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 three sentences, each adding distinct information: return content, non-extrapolation, campaign state. It is front-loaded with the main purpose. Minor deduction for the cryptic third sentence ('Campagne multi-machines non terminée') which could be clearer.
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 is simple with one optional parameter and an output schema exists (so return values need not be elaborated). The description adequately covers what is returned and key behavioral constraints. However, the missing explanation of the 'query' parameter creates a gap in completeness, as the agent has no guidance on how to use the sole input.
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 optional parameter 'query' with 0% description coverage, and the tool description does not explain its purpose or expected format. Given the low schema coverage, the description should compensate but fails to add any meaning to the parameter, leaving the agent to guess whether it filters results or something else.
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 states that the tool returns dated public benchmarks (machine, runtime, tok/s, reference) from the OutilsIA first-party source. It adds specificity about non-extrapolation and campaign state, distinguishing it from sibling analysis tools. However, it does not explicitly differentiate from siblings in a comparative way.
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. The constraints (not extrapolated, campaign not finished) imply boundary conditions but are not framed as usage instructions or compared to sibling tools like analyze_shared_report or check_pc_for_local_ai.
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 has a distinct purpose (analyze, check, explain, list, etc.) and the detailed descriptions make boundaries clear. However, the difference between 'reading a shared report' (analyze_shared_report) and 'reading a shared report to list installed models' (list_installed_models_from_report) or 'reading a shared report to list benchmarks' (list_benchmark_proofs_from_report) could cause an agent to pick the wrong one. There is also some overlap between these list operations that read a report versus simply displaying a pre-generated cockpit (render_machine_cockpit).
The majority of tools follow a consistent verb_noun pattern (e.g., analyze_shared_report, explain_bottleneck, list_installed_models_from_report, recommend_runtime). Minor inconsistency exists with the use of 'geo_audit' vs 'geo_kit' vs 'ratings' and the verb tense in 'list_benchmark_proofs_from_report' and 'list_first_party_measurements' departs from a simple pattern.
15 tools is at the high end of the ideal range (3-15), but each tool appears justified given the comprehensive scope of local AI assistance (hardware checking, model lookup, benchmarking, reporting, educational/reference tools). Slightly over-stuffed but still manageable for an agent.
The surface covers a complete workflow: check hardware, lookup models, benchmark, generate cockpit, explain bottlenecks, simulate upgrades, and reference documentation. The missing piece is the lack of 'update' or 'delete' operations, but this is by design, as the entire workflow is read-only. The set seems like a complete view of all possible read-only interactions with the domain.