audit

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It clearly indicates the tool is read-only/audit in nature ('run every check,' 'return one prioritised report'), establishing a non-destructive profile. However, it doesn't disclose behavioral details like runtime, network dependencies, permissions required, or failure behavior of individual checks, though the output schema existence helps somewhat. The core behavioral trait (aggregate, non-mutating) is conveyed, but depth beyond that is limited.

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 exceptionally concise: two short paragraphs totaling three sentences. Every line earns its place — the first states the function, the second positions it as the primary entry point, and the third gives a memorable mission framing. No filler or 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?

For a complex aggregate tool that runs 'every check,' the description explains the purpose well but with zero schema documentation coverage for 4 parameters. However, the output schema exists (has output schema: true), so return values don't need explaining. The main gap is parameter semantics — with 0% coverage, the description should illuminate what log_directory, code_directory, job_prefix, and max_log_age_hours control, which it does only implicitly via 'log' references. Still, the core intent and usage priority are complete enough for a first-call tool.

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 description coverage is 0%, so none of the 4 parameters are documented in the schema. The description mentions log_directory implicitly (the audit inspects logs), but doesn't explain job_prefix, code_directory, or max_log_age_hours specifically. Since coverage is 0%, the description should compensate but doesn't describe what each parameter means or their default behaviors beyond what titles provide. Given the 0% coverage, this is a notable 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 tool runs every check and returns one prioritised report, with a specific verb ('run'), resource ('every check'), and outcome ('one prioritised report'). It distinguishes itself from siblings like find_failing_jobs or check_log_freshness by being the aggregate 'run everything' tool that surfaces unknown issues. The mission statement 'what on this machine is broken right now and nobody has been told?' makes the purpose unmistakable.

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 explicitly states 'This is the tool to call first,' giving clear sequencing guidance. It contrasts with the granular sibling tools (find_failing_jobs, check_log_freshness, etc.) by being the comprehensive first-pass option. While it doesn't enumerate specific when-not-to-use scenarios, the 'call first' directive and the aggregate nature clearly position it against the specific checks.

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