list_log_files

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond annotations: it discloses that rotated files (e.g., adaptiva.2.log) match their base name, and it outlines the return structure (one row per file plus counts). These details help the agent anticipate results without overstepping.

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 structured with a clear purpose line, a parameter list, and a return note. It is longer than minimal but every sentence adds value; the rotated-file behavior and return-count detail are not filler. The front-loading of the purpose is effective, and the docstring-style formatting improves scannability.

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 list-metadata tool with an existing output schema (though not shown), the description is complete. It covers all parameters, gives matching semantics, and describes the return structure including aggregate counts. An agent can call this tool correctly without additional external knowledge, and the tool's simplicity (no nested objects, all optional params) aligns with this level of detail.

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 0% description coverage, so the description carries the full burden. It explains every parameter with type hints and concrete examples: source (omit for all), device (with sample names), role (enumeration), name (exact or glob, rotated matching), and limit (range 1-1000). This far exceeds minimal schema information and fully compensates for missing 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 begins with a specific verb ('List') and resource ('log files') and enumerates the attributes returned (device, role, purpose, size, time span). It clearly distinguishes this from content-searching siblings like search_logs by focusing on file metadata, and the parameter examples (e.g., 'content*.log') reinforce the listing scope.

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 for retrieving log file metadata but does not explicitly state when to prefer this over siblings like search_logs or summarize_errors. It does provide practical parameter guidance (e.g., 'omit for all sources') and explains how rotated files match base names, which helps correct invocation, but it lacks explicit when-to-use or when-not-to-use conditions.

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