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

Discloses significant behavioral nuance beyond the readOnlyHint annotation: "BEST EFFORT BY NATURE: this listens for a live broadcast rather than reading a stored position, and many vessels transmit less than once a minute, so a single call frequently hears nothing even for a ship that is definitely sailing." Also details coverage gaps (Persian Gulf, Strait of Hormuz, Gulf of Oman, Red Sea). This adds substantial context about reliability and operational characteristics.

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?

Although lengthy, every sentence earns its place: core purpose, best-effort caveat, parameter tuning, alternatives, coverage limitations, and count interpretation. Structured as a clear narrative that front-loads the purpose and then systematically addresses pitfalls. No redundancy or filler.

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?

The tool has no output schema, but the description specifies the return fields (position, speed, course, navigational status, destination). It covers alternatives, coverage gaps, parameter tuning, and the probabilistic nature of results. Given the tool's complexity (live AIS, partial coverage, varied transmission rates), this description leaves no critical context 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%, so parameters are already well-documented. The description adds value by explaining the effect of window_seconds on hit rate ("Hit rate scales almost linearly with this... a 10-second window will usually miss and a 40-second one often succeeds"). It also clarifies that mmsi can contain one or more vessels, but this is already in the schema. The additional behavioral insight about window_seconds justifies a score above the baseline.

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: "Where is a specific ship right now — live AIS position for one or more vessels by MMSI number." It clearly lists the returned data (position, speed, course, navigational status, destination) and distinguishes itself from siblings by explicitly recommending live_ships_in_area for area-based queries and vesselfinder_vessel for guaranteed last-known positions.

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?

Provides explicit when-to-use and when-not-to-use guidance: "Improve the odds with a longer window_seconds, or use live_ships_in_area if you know roughly where the ship is" and "use chokepoint_status for Hormuz/Suez/Bab el-Mandeb transit counts instead." It also clarifies the paid alternative (vesselfinder_vessel) and coverage limitations.

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