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

Annotations already declare readOnlyHint=true, so the description only needs to add context. It does this by disclosing the hourly update cadence, the specific computation (observed minus NOAA harmonic tide prediction), and the output components (per-station drivers, confidence, methodology_version). This goes beyond the annotation and helps the agent anticipate the response shape.

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?

The description is front-loaded with the core 'Returns...' statement and packs essential detail into a single dense sentence, followed by a clear usage directive and update note. It is somewhat long but every clause adds value; no unnecessary 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?

For a read-only data retrieval tool with one well-documented optional parameter and no output schema, the description is strong. It explains what the index represents, where it applies, what output fields to expect, and when to use it. It does not explain the history parameter, but the schema covers that, so the overall package is complete enough for an agent to invoke effectively.

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?

The input schema has 100% coverage for the single optional 'days' parameter, including its purpose, bounds, history mode, and Gold tier requirement. The description itself does not mention the parameter, but it need not because the schema fully documents it.

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 ('Returns') and names a concrete resource: a 0-100 US coastal water-level anomaly index. It further specifies the formula, station count, geography, and update frequency, making the tool's purpose unmistakable even among many siblings.

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?

The description explicitly states when to call the tool: 'Call when the user asks about storm surge, coastal flooding, king tides, or water levels above predicted tide, or when timing surge prep, port or marina operations, or coastal flood-exposure decisions.' It does not name alternatives or exclusions, but the usage context is clear and actionable.

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