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

With readOnlyHint/openWorldHint already declaring the safety profile, the description still adds substantial behavioral context: history is incomplete, unavailable history is free, baselines are not changes, pagination requires unchanged inputs, and the response carries an attributions array plus a disclaimer that must be passed through. It also warns "Never infer unpermitted work," which preempts a likely downstream misuse.

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?

Sentences are short, front-loaded and each carries distinct information (modes, baseline caveat, pagination, output pass-through). A few lines, e.g. "unavailable history is free," are terse to the point of ambiguity, but there is no filler.

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, yet the description still earns its place by flagging the attributions array and disclaimer as pass-through requirements. The remaining gap is identification of the property: it never explains the address-or-county+parcelId requirement or the exact-match constraint's implications.

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 33%, and the description covers just three of nine parameters (since, asOf, cursor), leaving address vs county+parcelId, city, zipCode and limit to the schema. Worse, it instructs the agent to "Use next_cursor" while the actual parameter is named "cursor," a naming mismatch that could confuse invocation.

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 ("Read immutable permit evidence") scoped to "an exactly matched property," plus the two modes (changes via since, point-in-time via asOf). It does not distinguish itself from the very similar sibling wa_permit_history, so an agent cannot tell them apart from the description alone.

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?

"Supply since for changes after that capture time, or asOf for versions known by that time" gives explicit mode-selection guidance, and "Initial captures are baselines, not changes" removes a real misinterpretation risk. Missing are when-not-to-use signals and any pointer to the sibling permit/sale-history tools for the cases this one does not cover.

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