Errors by page URL

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real context: the default sort is count descending, results carry affected-user counts and a TrackJS deep link, and the backing endpoint is disclosed. It omits default time-range behavior when startDate/endDate are absent, which is the main residual 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?

Three short sentences: what it returns, how it's sorted, and when to use it. The grouping dimension is front-loaded and nothing is repeated or wasted.

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?

With no output schema, the description usefully previews the return shape (error counts, affected users, TrackJS link) and default ordering, which is enough to call it confidently across 7 optional params. The one hole is what time window applies when no dates are supplied.

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 every parameter (page, size, sortBy, sortDirection, dates, application) is already documented. The description's 'sorted by count descending by default' merely restates the schema's default sortBy/sortDirection and adds no syntax or edge-case detail beyond it. Baseline 3 is appropriate.

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 verb+resource ('error counts grouped by the page URL') plus the aggregation dimension, which implicitly separates it from top_messages (grouped by message) and list_errors (individual events). It also names the underlying endpoint and the returned fields. It never explicitly names a sibling, so it stops short of 5.

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?

'Use to find which pages are most broken' gives a concrete selection context, which pairs naturally with top_messages for message-level triage. There are no explicit exclusions or named alternatives, so it lands at clear-context-but-no-exclusions.

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