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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantive behavior beyond them: figures come verbatim from the #196 dashboard/today endpoint with no invented numbers, and that a 'partial' completeness status means some checks were 'unavailable' and the agent must not declare the day clear. The weather_advisory caveat (always current conditions, never a forecast, even for a future target_date) is exactly the kind of non-obvious trait 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?

Content is front-loaded — purpose first, exclusions second, caveats third, example utterances last — and every section carries information. It is somewhat long and repetitive, with two consecutive "DO NOT" blocks and a trailing list of example phrasings that restates triggers already implied earlier.

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 one-parameter, read-only aggregator with no output schema, the description fully covers what comes back (trips, alerts with single next actions, stats), how to interpret degraded completeness, and where the data originates. Nothing an agent needs in order to call it correctly or report its results honestly 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 coverage is 100% and already documents the YYYY-MM-DD format and the omit-for-today behavior, so baseline would be 3. The description earns credit above baseline by explaining what passing a future date actually does semantically: it returns that day's brief, but weather_advisory within it remains current conditions rather than a forecast.

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 opens with a specific verb-resource pair ("OPERATIONAL ALERT DIGEST") and enumerates its contents: trips with roster/prep/vessel status, blocking/warning alerts with a single proposed action each, and quick stats. It explicitly distinguishes itself from get_dashboard (raw metrics) and get_operational_insights (multi-day trends), so an agent can route 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?

Both directions are covered: positive triggers are quoted ("what needs attention today", "morning brief", "are we ready for today", "what does tomorrow look like") and negative cases name the correct sibling tool for each exclusion. It also states that this tool only proposes, and that the named follow-up tool (resolve_prep_conflict, check_trip_waiver_compliance) performs the action.

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