pve_agent_file_read

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

Without annotations, the description covers key behaviors: read-only, prerequisites, no content logging in ledger, return format. However, it omits potential edge cases like file size limits or binary content handling. Still significantly transparent.

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?

Extremely concise: two sentences and a snippet. Key info is front-loaded with 'READ-ONLY'. Every sentence adds value—prerequisites, read-only assurance, sibling reference, return format, logging note. No wasted words.

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 has an output schema, and the description explains the return format and its implications (text round-trips exactly, ledger records only path). All necessary context for a read tool is provided, given the schema coverage and output schema.

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 schema already covers all parameters with descriptions (100% coverage). The description reiterates that the file path must be absolute, which is already in the schema. No additional semantics are provided beyond the schema's definitions.

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 'READ-ONLY: read a file from inside the guest via the qemu-agent.' It specifies the action (read), resource (file inside guest), and distinguishes from the sibling tool pve_agent_file_write for writing. The purpose is unambiguous.

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?

Explicit prerequisites are given: PROXIMO_ENABLE_AGENT=1, VMID in PROXIMO_AGENT_ALLOWLIST, running guest agent. It clarifies that no confirmation is needed due to read-only nature. It directly tells when to use the sibling tool for writing. Full guidance.

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