host_log_scan

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

Beyond readOnlyHint and idempotentHint, it reveals reading the last `lines` entries from specific logs, matching known trouble patterns, and returning an empty list if none found. This adds concrete behavioral detail without contradicting annotations.

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 efficiently structured: a one-line summary, a behavioral paragraph, a usage tip, and parameter details. Every sentence adds value without redundancy.

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 annotations and output schema, the description covers input, behavior, output (empty list), and performance guidance. It mentions return fields (severity, source, message) even though output schema exists, enhancing completeness.

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 fully explains each parameter: host_name (filter or null), lines (count, default 500), target (optional, defaults). This adds critical meaning beyond the schema types and defaults.

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 starts with '[READ] Scan recent ESXi host syslog lines for error/warning patterns', clearly stating the verb 'scan' and the specific resource 'ESXi host syslog lines' with a focused purpose. It distinguishes from sibling tools that list or retrieve data without pattern filtering.

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 notes that only errors/warnings are returned, keeping output small, and suggests filtering with host_name for speed. It implies when to use (need error patterns) but does not explicitly state alternatives or when not to use, though it effectively guides efficient usage.

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