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

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is to add context — and it does: newest-first ordering, the exact fields per run (scheduled_at, first attempt, delay, attempts, status, last response code), and that since/until filter on scheduled_at rather than completion time. It doesn't mention retention limits or the default/max page size, which keeps it from a 5.

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?

Compact and front-loaded — the returned fields, then filter semantics, then pagination. The trailing REST endpoint note (GET /v1/jobs/{id}/runs) adds little for an MCP caller and is the one expendable element.

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, listing the per-run fields is genuinely necessary and is present, and the date-filter and pagination behavior is covered. Gaps remain on the status filter and limit bounds, and the cursor/next_cursor naming mismatch leaves a small ambiguity for a 7-parameter tool.

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 only 29%, so the description has to carry weight: it clarifies that since/until are ISO 8601 and apply to scheduled_at, and that paging uses a cursor. However, the 'limit' and 'status' filter parameters are never explained, and it calls the paging token 'next_cursor' while the actual parameter is named 'cursor', which risks confusion about what to pass back.

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?

Opening phrase 'Trigger log, newest first' plus the enumerated fields makes clear this returns the run history for a job, distinguishing it from the single-run sibling get_run (though it never names that sibling). The specific resource (runs of a job) and the ordering are both stated explicitly, so an agent knows what it gets.

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?

Usage is implied by the data described (paginated run history with date filters), but there is no explicit when-to-use/when-not guidance and no reference to get_run or get_stats as alternatives. The agent must infer that this is the bulk-history tool while get_run fetches one run.

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