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

Annotations already declare readOnly and non-destructive, and the description adds real behavioral context: health is UNKNOWN (yellow) unless include_health is set, the live-health path costs one Amazon report per outpost and is slower, and only ACTIVE marketplaces (>= 10 units sold+pending in last 30 days) are listed while others collapse into dormant_summary. It also discloses the rules version (2026-10-15) governing the traffic light.

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?

It leads with what is returned and then covers defaults and flags, so it is front-loaded and nearly every clause carries information. It is a single dense run-on paragraph, though, and the closing reporting instruction ('Always state the period and that amounts are VAT included') is agent guidance rather than tool semantics, slightly diluting conciseness.

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?

There is no output schema, and the description compensates by enumerating the returned fields, the traffic-light vocabulary, the dormant_summary aggregation, and the ACTIVE-marketplace threshold. For a four-parameter, zero-required read tool, an agent has everything needed to call it correctly and interpret the result.

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 only 50%, and the description compensates precisely: it defines cockpit_id's fallback resolution order and the full effect of include_health on both latency and the health status value. The two undocumented schema parameters are the two the description explains best, so an agent knows exactly what each flag does.

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 resource (monthly cockpit per outpost) and enumerates exactly what it returns: MTD sales, target, projection, ACoS/TACoS, open findings, and a rosso/giallo/grigio/verde traffic light with reasons and next action. This is clearly distinguishable from siblings like list_cockpits, save_cockpit, set_cockpit_target, and get_dashboard_data.

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?

Explains the default selection behavior when cockpit_id is omitted (first active cockpit, or all visible outposts if none), and gives a clear when-to-use tradeoff for include_health (live Account Health, slower, one Amazon report per outpost). It does not explicitly name a sibling tool (e.g. list_cockpits) to fetch a cockpit_id, so the alternative path is implied rather than stated.

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