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

Annotations already declare readOnly/openWorld/idempotent, but the description adds substantive behavior beyond them: the response fields (fact, place, time, source_url, age_seconds, stale, confidence), the stale-marking mechanism tied to max_age_minutes, the failure mode ("it says so instead of guessing"), and cost/auth ("Free, no sign-up"). This is exactly the extra context annotations 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?

Front-loaded with the core capability, then usage list, then three illustrative questions, then return shape and limits. Every sentence carries distinct information — the example questions do real work in disambiguating the topic enum rather than padding.

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 correctly spells out the return fields, and it discloses unsupported domains and no-auth access. Gaps are minor but real: measurement units, what confidence values mean, and how place versus lat/lon interact when both are given.

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 only 40%, so the description must compensate and largely does: it expands the topic enum into concrete question forms, clarifies that a place can be a name or lat/lon, and implicitly defines max_age_minutes via "age_seconds" and "stale". It stops short of stating precedence when both place and lat+lon are supplied, or units/defaults for numeric inputs.

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?

"Get a cited, time-stamped real-world fact for any place on Earth" names a specific verb and resource, then enumerates the exact fact domains (weather, river level, earthquakes, AQI, alerts). An agent can distinguish this from the surrounding identity/attribution/admin siblings without reading 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?

It gives explicit positive selection criteria ("Use it for: current weather or temperature, river level or flood status, earthquakes..., air quality, US weather alerts") and explicit exclusions ("Not connected yet ... road closures, power outages, burn bans"). What is missing is any routing to an alternative when the tool declines; no sibling tool is named for the unsupported topics.

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