check_recent_errors

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

With no annotations, the description carries the full disclosure burden. It transparently reveals the scoping behavior: only recent files, only last lines, and explains the rationale (avoiding stale failures). It does not reveal return format or pagination behavior, but the output schema exists to cover that gap.

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?

Two tight sentences plus a clarifying follow-up. Every sentence earns its place: the first states the action, the second explains the scoping rationale. Zero waste, efficiently front-loaded.

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 3-parameter tool with no annotations and 0% schema coverage, the description provides the core behavioral contract (time-boxed tail-scanning). The output schema exists, reducing the need to describe return values. It could slightly improve by explicitly defining parameter bounds, but overall it is reasonably complete for its complexity.

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 0%, so description must compensate, but it only explains the 'tail' and 'recent' concepts implicitly through the prose rather than mapping to specific parameters (within_hours, tail_lines). The parameters themselves (directory, tail_lines, within_hours) are fairly self-explanatory by name and defaults, but the description doesn't explicitly define their semantics or bounds.

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 states a specific verb+resource ('Scan the tail of recently-written logs for error signatures') and clearly distinguishes itself from siblings. The detail about 'only recent files and only their last lines' explains the behavioral scoping that differentiates it from generic log-search tools like find_failing_jobs.

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 explains the when ('recently-written logs') and why the scope matters (failures fixed last week should not reappear). It implies this tool is for time-boxed error scanning, though it doesn't explicitly name sibling alternatives or state when NOT to use it. Clear context but no explicit exclusions.

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