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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety is covered. The description adds real value beyond that: the required api:read scope and the fact that the response carries app_url for the Alerts settings screen. It stops short of stating response shape/size limits, keeping it from a 5.

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 definition then enumerated by view, with no filler sentences. Dense but long semicolon-chained sentences make it slightly harder to scan than necessary, keeping it below the top mark.

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?

No output schema exists, and the description covers return contents per view mode, the auth scope requirement, and a cross-reference for the adjacent task. An agent has everything needed to choose a view and call it 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 67% and the description compensates well, spelling out what each view returns (id, cron_id, name, interval, query, predicate, delivery_channels, edge_triggered, status, last run) and what catalog exposes (endpoints, params, predicate field paths with units). It largely restates the status enum from the schema and does not describe cron_id format beyond 'one signal by cron_id', so it falls just short of a 5.

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 ('YOUR signals (alerts)') and immediately defines what a signal is (scheduled standing checks that notify). It explicitly separates this from get_fired_signals, which covers signals awaiting an answer, so the agent can distinguish 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?

Gives per-mode guidance: view=list is marked default with its status filter, view=detail requires a cron_id, and view=catalog is framed as the prerequisite source of truth for building save_signal's query and predicate. It also redirects to get_fired_signals for fired alerts awaiting a response.

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