aras_get_logs

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Given that no annotations are provided, the description carries the full burden — and it delivers by revealing the dual-source behavior (filesystem plus database) that the tool name alone would never divulge, as well as the configuration prerequisite for file logging. The fresh-install note ('possono essere entrambe vuote') preemptively explains surprising empty results. It still doesn't mention effects on the system, performance implications of includiDatabase, or whether it's read-only, but the disclosures are far above what generic prose would provide.

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?

Three sentences in Italian, front-loaded with the core purpose and reserving the second part for a genuinely decision-relevant edge case. No fluff, with the important scoping details (both sources, empty-on-fresh-install, configuration prerequisite) all present. A small nit: the architecture information could lose a few words, but it is already lean.

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 main complexity of this tool is its dual backend, and the description addresses it head-on, including the conditions under which each source may return nothing. Since there's no output schema, a brief note on how the two sources would be combined or formatted would make it more complete, but the description is already a strong package for an agent to call this tool 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 coverage is 67%: righe and filtro have descriptions with ranges and an example regex, while includiDatabase is left undocumented. The description partially compensates by explaining the file-vs-database architecture that gives 'includiDatabase' meaning, effectively clarifying that it asks the request to consult the database source. However, it adds no parameter semantics beyond the schema — nothing about the regex flavor, how rows are read from the tail, or the meaning of the boolean default.

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 statement 'Log di Aras da due sorgenti' gives a specific verb and resource, further clarified by naming the two exact log sources (server files for 'Innovator, OAuth, Client' and the 'SystemEventLog' database ItemType), which exceeds a tautological restatement of the name. It accurately sets expectations that this tool reads logs from two heterogeneous backends. However, it doesn't position itself against obvious siblings like aras_read_file, so differentiation from similar read tools is left implicit.

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 when the tool applies by naming the exact sources it covers, and it surfaces a real usage pitfall: on fresh installs both sources may be empty and file logging must be enabled in server configuration. This is valuable caveat guidance for interpreting results correctly. It stops short of explicit when-to-use/when-not-to-use routing or side-by-side comparison with alternatives, leaving some inference to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.