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

Annotations only give a blanket destructiveHint=true, but the description differentiates the operations: summarize incurs a billed LLM call against org AI credits, acknowledge is idempotent and only marks read for the caller, and dashboard dismiss/snooze is a per-caller view change that leaves the underlying item unchanged. That is exactly the kind of nuance the annotations cannot express.

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?

Front-loaded with the write-scope and each action's effect in a single dense sentence, followed by the sibling routing and the describe pointer. Every clause is informative, though the stacked parentheticals make it slightly heavy to parse.

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 5-action, 22-parameter write tool with no output schema, it covers what each action does and where to find full parameter details. It stops short of describing what each action returns, but the describe pointer partially compensates.

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 the schema already carries the parameter semantics (including the nuanced user_id/subcategory/category notes), making 3 the baseline. The description adds only the pointer to action='describe' for the full reference rather than new per-parameter meaning.

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?

States a specific verb+resource ('Fastio events (write)') and enumerates the three distinct write capabilities (summarize, acknowledge, dashboard dismiss/undismiss) with their effects. It explicitly distinguishes itself from the read sibling by saying 'Reads are on `event`', so an agent can separate the two without opening either 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 read/write split against the `event` sibling is stated explicitly, which is the primary routing decision. It also points to action='describe' as the authoritative reference for the action/param catalog, giving a clear fallback when details are needed.

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