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

Annotations already declare readOnlyHint=true, so the safety profile is covered, yet the description still adds real behavioral content: missing or old data must remain visible, supplied prices are scenarios not a CMA or appraisal, and licensed listing/price-index trends are substituted when snapshots are paused. It also mandates that the 'attributions' array and professional-advice disclaimer be passed through to end users, which is a downstream obligation an agent could not infer from the schema. It stops short of covering failure modes or partial-result 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?

Three sentences, front-loaded with what the tool produces before the caveats, and the pass-through instruction lands last where an agent will still read it. It is dense but every clause carries a constraint; the only mild cost is legal-register phrasing ('non-affiliation line') that slows parsing.

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?

Return values need little explanation because an output schema exists, and the description covers the disclaimer and attribution obligations well. The gap is on the input side: for a 7-parameter tool with 14% schema coverage and several optional nested objects, the description says nothing about how to decide whether to supply property, deadlines, or monthlyPayment, leaving the agent's call construction under-informed.

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 description coverage is only 14% across 7 parameters, so the description carries the burden and mostly does not. It alludes to the scenarios input and to county/property/market data in passing, but never explains the deadlines sub-object, monthlyPayment, includePermits, the 2-3 scenario array bound, or the county identifier format. An agent must open the nested $defs to learn anything about how to populate the 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?

The description gives a specific verb and artifact: 'Prepare one seller briefing that combines proposed sale-price scenarios with available county property records and dated market context.' That is concrete enough to distinguish it from single-purpose siblings like wa_comps or wa_monthly_payment. It never names a sibling it is not, though, so an agent comparing it against wa_compare_seller_scenarios or wa_research_packet must infer the boundary from the word 'packet' 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?

Usage is implied rather than stated: the word 'packet' plus the list of combined inputs signals a multi-artifact briefing, and the fallback clause about paused sale-price snapshots hints at degraded conditions. But there is no explicit 'use this when X, use wa_compare_seller_scenarios when Y', and no prerequisites such as which county values are valid or when a property locator is required versus optional.

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