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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=true, but the description goes well beyond them: it explains *why* it is destructive (every on-duty member is paged by push, SMS and/or voice), what escalation does if nobody acknowledges, and what non-idempotency concretely means ('a second call pages the team again'). It also discloses the return payload shape (the new alert incl. its id), which no output schema provides.

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?

Four dense sentences, front-loaded with the operation mode and resource, then stakes, then usage restriction, then return/endpoint. No filler or restated name, and each sentence carries decision-relevant information.

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?

With no output schema, the description still tells the agent what comes back (the new alert including its id), and it covers the safety profile, escalation behavior, and usage boundary. Nothing an agent needs to call this correctly or avoid a mistaken page is missing.

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% and every parameter (team_id, title, text, category, severity, external_id) is already documented in the schema, including cross-references to signl4_list_teams and signl4_list_categories. The description adds no per-parameter semantics beyond that, so the baseline 3 applies.

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?

Opens with an explicit verb+resource and mode label ('WRITE: raise a new alert in a SIGNL4 team'), which immediately separates it from read siblings like signl4_get_alert and state-change siblings like signl4_acknowledge_alert or signl4_close_alert. The endpoint (POST /v3/signls) reinforces the resource identity.

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?

States both the positive condition ('Only use it when the user clearly asked to alert the team') and an explicit exclusion ('never for tests unless they said so'), which is exactly the ambiguity an agent would otherwise guess at. The real-world consequence sentence gives the agent the stakes needed to decide.

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