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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description is free to add provenance instead: published NZ government hazard data from NZS 1170.5, GNS Science, MfE and NIWA. That sourcing is genuinely useful for judging credibility and recency of the numbers, though nothing is said about data vintage, refresh cadence, or coverage gaps for properties lacking hazard data.

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?

Front-loaded with the purpose, then output contents, then provenance, then the supported-ticker list — a sensible priority order with no filler sentences. It is somewhat list-dense in the middle, but each clause carries distinct information rather than restating the name or title.

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 an output schema present, the description correctly focuses on scope, inputs and provenance rather than restating return values. It is nearly complete for a single-parameter read tool, lacking only the failure mode for unsupported tickers and any note on how often the underlying hazard data is refreshed.

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% for the single ticker parameter, so baseline is 3. The description goes beyond the schema's three inline examples by listing the full supported ticker universe, which materially narrows the agent's guesswork about valid inputs — the main semantic gap that remains is the absence of a defined error behaviour for unsupported tickers.

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?

Names a specific verb and resource — climate/natural hazard risk analysis — and pins the scope to NZX property company portfolios, which separates it from adjacent siblings like get_climate_gap_analysis and get_esg_data. It also enumerates the exact outputs (composite scores, NZS 1170.5 seismic zones, flood, liquefaction, coastal proximity, SLR exposure) so an agent knows precisely what it returns 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?

The 'Works for: KPG, ARG, PFI, VHP, IPL, SPG, CDI, GMT, PCT, APL' line effectively bounds the valid input domain, which is useful usage context. However, it never states when to prefer this tool over neighbours such as get_climate_gap_analysis, get_esg_data, or get_property_portfolio, nor what happens for out-of-list tickers. Usage is implied rather than guided.

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