Составить или поправить рассылку

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

Beyond the annotations, the description discloses important behavioral traits: a draft will not send until started, edits don't work once a broadcast has begun, selection criteria replace rather than merge, omitted criteria remain unchanged, and HTML markup is validated at save time. This is substantial value beyond the readOnly/destructive hints.

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 description is dense but every sentence earns its place: it distinguishes create/edit behavior, names the cancellation sibling, explains selection-criteria semantics, and notes HTML validation. The most important behavioral distinction is front-loaded in the first sentence.

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 complex tool with 15 parameters and no output schema, the description covers the critical behavioral context: when the tool creates vs edits, when editing is impossible, how to handle a started broadcast, and how selection updates behave. Combined with the 100% schema coverage, an agent has enough to call the tool correctly.

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 schema already documents all parameters. The description adds meaningful semantics for the key `broadcast` parameter (new vs edit, draft vs scheduled vs started) and clarifies replacement behavior for selection criteria, which is not fully captured by the schema property descriptions.

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 action and resource: without `broadcast` it creates a broadcast draft; with `broadcast` it edits an existing draft or a scheduled-but-not-yet-sent broadcast. It also clearly distinguishes itself from sibling tools `broadcasts_start` and `broadcasts_cancel`, so an agent can tell when this tool applies.

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 gives explicit usage rules: omit `broadcast` to create a draft, provide it to edit a draft or scheduled broadcast, and do not attempt to edit an already-started broadcast — instead use `broadcasts_cancel`. This is direct guidance with named alternatives and clear conditions.

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