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

Far exceeds the annotations: it discloses the API-key requirement and header format, a daily question limit on free keys, the disclaimer attached to answers, the public-data-only sourcing, the async job_id/wait-budget behavior, and the x-untrusted marking of addresses and answer text. The readOnlyHint=false and openWorldHint=true annotations are consistent with a tool that can spawn a job and reads external data; nothing here contradicts them.

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 action and examples, then auth and return behavior, which is a sensible ordering for a multi-faceted tool. It is on the long side for a three-parameter tool, and 'The result is data about a property' adds little alongside the more precise x-untrusted sentence that follows it.

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?

Covers everything an agent needs for a tool with this complexity: auth, rate limits, async fallback, untrusted-input handling, and the sibling that performs the full analysis. An output schema exists, yet the description still names the return shape ({text, address} or job_id), which is a bonus rather than a redundancy.

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 parameter meaning and it largely does: 'question' is described by example, and the address/report_id relationship is spelled out, including the non-obvious rule that the address is read from the report when report_id is given. It does not explicitly state that address and report_id are optional/nullable or what happens if neither is supplied, leaving a small gap.

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 ('Ask a plain-language question about one property') and enumerates concrete question types (flood zone, school district, tax bill, report number meaning). It explicitly carves out the boundary against analyze_property, so an agent can distinguish it from the sibling without opening a 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 when to use (free-form property questions), how to supply context ('either the address or the report_id of a report you already have'), and names the alternative with its purpose ('It is not the full analysis: analyze_property gives the valuation'). The fallback path when the call runs long (pass job_id to get_job) is also stated, which is exactly the routing an agent needs.

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