debug_get_errors

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It conveys a read-only operation and names the content classes returned, but it does not disclose what happens when no active session exists, the return structure/format, or behavior when a session has zero errors. For an introspection tool with zero annotation coverage, this is a meaningful 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?

The instruction portion is a tight single sentence with no wasted words, and the content specification is front-loaded. The opening '[Arch Debug] Arch connects to live sessions...' sentence adds mild product context but is partly redundant with the tool's family and could be trimmed; this prevents a perfect score.

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 is simple (2 optional params, no output schema), and the description lists what it returns (errors, warnings, escalations, constraint failures), which covers the content dimension. However, with no output schema present, the return structure/format is entirely undocumented, and the live-session precondition is implied rather than stated. Adequate but with clear gaps.

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 100% (both sessionId and includeWarnings are documented in the schema), so the baseline is 3. The description adds nothing beyond what the schema already states about the active-session fallback and warning inclusion. It doesn't compensate further, which is acceptable given full schema coverage.

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 clear verb+resource ('Get all errors and warnings from the session') and adds specificity with 'Includes escalations and constraint failures,' which meaningfully narrows what is returned. It distinguishes itself from siblings like debug_session_history and debug_traces by its error/warning focus, though it doesn't name those siblings explicitly.

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 gives no guidance on when to choose this tool over alternatives such as debug_traces, debug_analyze_session, or debug_harness_logs. The opening product-context sentence ('Arch connects to live sessions...') implies a live-session dependency but never states when this tool is appropriate or when it is not. No exclusions or alternative routing is provided.

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