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

Annotations already cover the safety profile (readOnly=true, destructive=false), and the description adds substantial behavioral context beyond them: open data with no API key, anonymous rate limits (60/hour, 300/day per IP and session), key-based higher limits with anonymous fallback, SI normalisation, provenance, and source licence warnings. This is exactly the value-add structured fields cannot carry.

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 core purpose, date constraints and period/property choices are front-loaded, and nearly every sentence carries an actionable constraint (range limit, statistic matching, rate limits). It is dense and slightly run-on, and 'TerraMCP is a Wrench AI service' is the one throwaway clause, but overall the length is justified.

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 6-parameter read-only query with no output schema, the description covers the essentials an agent needs to call it correctly: valid ID space, statistic/property pairing, interval choice, date ordering and span limits, and even the rate-limit envelope. Nothing material 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%, so the schema already documents all six parameters, setting a baseline of 3. The description nonetheless adds decision-relevant meaning the schema lacks — that rainfall pairs with 'total', levels with 'min/max', and that station_id is a Hydrology SUID rather than a flood ID — lifting it above 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?

States a specific verb+resource ('Get qualified EA Hydrology ... time series') and enumerates exactly which properties are served (flow, level, rainfall, groundwater), which cleanly separates it from UK siblings like nrfa_get_timeseries, sepa_series and rainfall_latest. An agent can identify the source family without opening the 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?

Gives real selection guidance: use a Hydrology station SUID, match property to a supported statistic (rainfall→total, levels→min/max), pick daily vs 15min, and keep ordered dates ≤366 days apart. It also implicitly routes away from flood tools by warning the ID is 'not a flood-monitoring station ID', but it never names an alternative tool explicitly.

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