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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered by structured data. The description adds useful non-annotation context: output is normalised to SI (mm) with source provenance, and 'latest ... only' implicitly explains why idempotentHint=false (results shift over time). It still says nothing about authentication mechanics beyond the label 'authenticated router', rate limits, or what an empty result means.

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?

Three short sentences with the resource and units front-loaded before the parameter nuance. The opening 'TerraMCP authenticated router: rainfall_latest' is largely a restatement of the tool name and could be trimmed, but overall the text is tight and earns most of its space.

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?

With no output schema, the description helpfully states what comes back (normalised SI values in mm plus source provenance), which covers the main return-value question. It is still thin for a tool in a dense station/reading family: no mention of how to obtain a valid station_id, whether missing data is returned, or result ordering.

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 0%, so the description must carry the load. It does clarify that station_id refers to an 'EA flood-monitoring station' and that latest_n is readings 'per measure' with a default of 1, which is real added meaning. It omits the identifier's accepted form/pattern and any guidance on sensible latest_n values up to the 100 cap.

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 and resource ('Returns ... Latest rainfall readings ... in mm, for an EA flood-monitoring station') and adds scope ('latest only', normalised SI, provenance). It is clear what the tool does, but it never names or contrasts with the closest siblings (flood_get_readings, ea_hydro_series, rainfall_stations), so differentiation is left to inference.

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?

'Latest rainfall readings only, in mm, for an EA flood-monitoring station' implies this is the point-reading companion to a time-series tool, and 'latest_n defaults to 1' hints at bounded retrieval. However, there is no explicit when-to-use rule, no exclusion, and no pointer to the sibling that retrieves historical series or the one that resolves a station_id.

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