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

Beyond the annotations, it discloses replace semantics ('what you leave out of a change is cleared, not kept'), the filing cadence and local-time behavior, that the issue is filed under the caller's identity with the same rules, notifications and watchers, template placeholder expansion, overlap handling (new issue filed anyway and linked), paused-project catch-up behavior, and validation refusal with a reason. These are exactly the consequences an agent needs before invoking a destructiveHint tool.

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?

The action and the omit-clears warning are front-loaded, and every sentence carries operational information. It is long and uses some emphatic phrasing ('the WHOLE of it as you write it here', 'on YOUR clock'), but the length is justified by the 13 parameters and the destructive upsert behavior.

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 destructive 13-parameter upsert with no output schema, the description covers authorization, replace semantics, cadence, template expansion, overlap behavior, catch-up behavior and failure modes. The main gap is that it does not say what is returned on success (e.g. the schedule id or the created schedule), leaving the agent to infer the response shape.

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%, so the baseline is 3, but the description adds cross-parameter meaning the schema does not: that 'nextDay' combined with 'every' defines the cadence, that omitted fields are cleared on update (not left as-is), and that summary placeholders are resolved on the filing day. It does not add anything for individual fields like dueInDays or labels beyond what the schema already says.

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 opening sentence gives a specific verb and resource ('Add a recurring issue to a project') and immediately covers the update case ('or change the one named by id'). An agent can distinguish this upsert-style schedule tool from list_issue_schedules and delete_issue_schedule without opening any schema.

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?

The description clearly states the add-vs-change condition keyed on 'id' and names the authorization gate ('The project's lead, the company's owner or an admin only'). It does not explicitly name list_issue_schedules as the way to obtain the id, though the schema does, so this falls short of a full when/when-not/alternatives treatment.

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