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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered by structured data. The description adds genuine behavioral context beyond that: the full set of returned fields and the pagination contract (20 per page, cursor for more), which the annotations do not convey.

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 tight sentences: usage trigger first, return payload second, exclusion last. No filler and nothing repeated from the annotations.

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 specified; the description nonetheless summarizes them usefully. With pagination covered and the exclusion stated, an agent has everything needed to call this correctly against its siblings.

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 100% and each of the three parameters (limit, cursor, projectId) is documented in the schema, so the baseline is 3. The description adds a small amount on top by framing the paging workflow ('20 per page by default, with a cursor for more'), which helps the agent understand how limit and cursor interact.

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 concrete verb and resource (list cron jobs / scheduled tasks) and enumerates exactly what comes back: id, name, schedule, target origin, method, enabled state, last run status and time. It also explicitly delimits itself against the sibling get_job_runs with 'Not for a job's full run history.'

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 a clear trigger ('when someone asks what cron jobs or scheduled tasks they have, or which ones last failed') and one explicit exclusion (full run history). It stops short of naming the alternative tool (get_job_runs) the way the strongest definitions do, so the routing is implied rather than spelled out.

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