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

Annotations already declare readOnly/destructive/openWorld, but the description adds non-obvious traits the annotations can't convey: it's free with no account, the document is 'read in the request, answered, and dropped — nothing is stored on either side', and the caller should confirm in one line what was sent and that it wasn't kept. The idempotentHint=false annotation is not addressed, but nothing contradicts the stated behavior.

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-loads the core action and the operational instructions are tight, but it spends a sentence on pitch/marketing ('their private file, our joined records, one answer') that doesn't help an agent invoke the tool. The example invocations earn their place; the sloganeering does not.

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?

An output schema exists, so return values need not be explained, and the description covers the privacy lifecycle, cost, required slug discovery, and the text-vs-claim branch. For a 4-parameter tool with a nested `context` object, the remaining gap is that the `context` sub-fields (fromMonth, radiusFeet, subjectAddress) are only explained in the schema and tied to 'tools that ask since when' in the description only loosely.

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?

With 75% schema coverage the schema carries most parameter detail, but the description adds material routing semantics: `tool` is not an enum and must be sourced from what_we_have_for_you, `claim` replaces `text` for 'claim-check', and text must be passed verbatim ('do not summarise a P&L before sending it'). The `context` sub-fields are left to the schema.

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 (reads a person's document against the Minneapolis–St. Paul public record) and a concrete output (a table that cites the file behind every cell). It also positions itself against the public-record-only siblings by framing itself as 'the half of the platform the public record cannot do alone', so an agent can distinguish it from twin_cities_lookup/twin_cities_records.

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 a clear invocation prerequisite ('Get the slug and what to bring from what_we_have_for_you', cards with api_tool=true list `bring`) and three worked example invocations mapping real-world asks to the `tool` slug. It doesn't state when NOT to use it (e.g. when the data is already public and twin_cities_lookup suffices), so it stops short of full when/when-not routing.

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