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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: results are individual job attempts, filtering is by GitHub status, and a job whose runner failed to start can still report as queued. Pagination behavior is also mentioned, though return shape detail is left to the output schema.

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?

Four sentences, all front-loaded and information-dense: purpose, result granularity, filter semantics, and pagination/scope. No redundant restatement of the tool name or schema.

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?

An output schema exists so return values need not be described. The description covers scoping, pagination and filter semantics, which is sufficient for an 8-parameter list tool; the time-range limits are handled by the schema. It is complete without being exhaustive.

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 a baseline of 3 is warranted. The description nonetheless adds meaning beyond the schema for repositoryId (omitting it means all accessible workspace repositories) and cursor (advance it for more results), plus the status/failure filtering intent.

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 specific verb ('find') plus resource ('GitHub Actions jobs in Runzumi') and scope ('recent, failed, queued or running'). It also defines the unit of a result ('one job attempt'), which cleanly separates it from siblings like get_run, get_run_statistics and search_run_logs.

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 concrete usage rules: omit repositoryId to span all accessible workspace repositories, follow the cursor for more results, and how the status filter maps to GitHub status semantics. It does not name alternative tools (e.g. get_run for a single attempt) or state when not to use this tool, so it stops short of a 5.

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