perch_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 does reveal meaningful behavior: errors are buffered (persistent state), three distinct sources are merged, and clear:true resets the buffers — a mutating side effect. It stops short of describing the response shape or what happens if buffers are empty.

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 dense sentences with zero waste: the first enumerates the three error sources, the second covers the one option. Front-loaded and complete.

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 one-optional-parameter tool with no output schema, the description adequately covers sources and buffer semantics. The main omission is any hint at the returned structure or ordering of the aggregated errors.

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%, so the single 'clear' parameter is already documented as 'Clear buffers after reading. Default false.' The description adds timing context ('after a fix') but no new syntax or format detail, so it sits at the high-coverage baseline.

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?

States a specific purpose — aggregating editor syntax errors, buffered runtime/page errors, and console tail into one call. It even names the underlying API (window.getEditorSyntaxErrors). It does not, however, distinguish itself from the sibling perch_console, whose territory the 'console tail' overlaps.

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 framing 'Error triage in one call' implies a diagnostic context, and it advises 'Use clear:true to reset buffers after a fix.' But there is no explicit when-to-use-this-vs-perch_console guidance and no exclusions, leaving the choice between overlapping tools to inference.

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