analyze_shared_reportLit un rapport public OutilsIA Local Cockpit déjà créé par l'utilisateur. Accepte uniquement une URL exacte https://outilsia.fr/r/... et ne donne aucun accès à la machine.
| Name | Required | Description | Default |
|---|---|---|---|
| usage | No | polyvalent | |
| report_url | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| decision | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable context: 'ne donne aucun accès à la machine' (no machine access) and the strict URL format requirement. This goes beyond what annotations provide, clarifying security and input constraints.
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 two concise sentences in French, front-loaded with the action. Every word adds value, and there is no redundant or vague phrasing. It is well-structured and to the point.
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?
Given the presence of an output schema (no need to describe returns) and two parameters, the description covers the core purpose, URL constraint, and security. However, the missing description of the 'usage' parameter is a notable gap that reduces completeness for a tool with a dropdown enum. The description is adequate but not fully comprehensive.
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?
With 0% schema description coverage, the description must explain parameters. It partially covers 'report_url' by specifying the exact URL format, but completely omits the 'usage' parameter (enum with 7 values and a default). The agent has no guidance on what 'usage' controls or how to set it, leaving a significant gap.
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 the action ('Lit un rapport public') and the specific resource ('OutilsIA Local Cockpit déjà créé par l'utilisateur'). It specifies the exact URL format, distinguishing it from sibling tools that list or explain parts of a report.
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?
The description implies usage when the user has an existing report URL and wants to read it. However, it does not explicitly state when not to use this tool or mention alternative tools (e.g., listing models or benchmarks from the report instead). The statement 'Accepte uniquement une URL exacte' offers some guidance but lacks completeness.
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.