get_runtime_errors

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

With no annotations, the description carries the full behavioral burden, and it does most of that work: it discloses that only active OPEN errors are returned by default, the session/24h time window, the source coverage, and the grouping/location format. It stops short of explicitly declaring the operation is a safe read (no mutation) and says nothing about pagination or rate behavior.

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 sentences, zero filler, and the imperative call-to-action is front-loaded before the return-value detail. The capitalized ALWAYS is slightly loud but functionally effective for routing.

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 5-parameter, all-optional, no-annotation tool with no output schema, the description supplies the essential context: trigger conditions, scope, time window, and return grouping. It is nearly complete, missing only an explicit statement that it is a non-mutating read and any note on how limit interacts with grouping.

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 baseline is 3, but the description genuinely adds meaning by mapping its wording onto parameters: 'active OPEN' implies include_resolved defaults false, and 'current dev session (or last 24h)' clarifies the all_sessions/since_minutes behavior. That is real added semantics rather than restatement.

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 precise verb+resource and goes well beyond a label: it enumerates the error sources covered (runtime, bundler Vite/Next.js/Storybook, TypeScript, browser), the time window (current dev session or last 24h), and the return shape (grouped by signature with file:line). The 'ALWAYS CALL THIS TOOL FIRST' clause also positions it relative to the sibling set (resolve_error, check_fix, get_error_detail) as the entry point.

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?

It gives an explicit and aggressive trigger list ('error, bug, crash, broken component/page, or asks you to fix/debug anything') and states ordering ('call this first'). What it lacks is any when-not condition or a named alternative for the follow-up case, so an agent must infer that the siblings are used after this call.

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