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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety bar is low; the description still adds real context: sources have independent coverage, timestamps and required attributions, which warns the agent about mixed provenance and licensing obligations. It also flags interpretation limits (no attendance, quality or walking time). Missing details like result caps or per-source failure behavior keep it at 4.

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?

Roughly 90 words with the three data domains front-loaded and no filler sentences. The middle is heavily packed into comma-chained clauses, which costs some scannability but every sentence carries information.

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?

For a 10-parameter, multi-source tool with an output schema present, the description covers what is fetched, the geography selector, the pairing constraint, filter logic, provenance caveats and explicit non-goals. Return-value explanation is not needed given the output schema. Sufficient for correct invocation.

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 30%, so the description carries real burden, and it does clarify pairing rules, exact four-digit schoolCode and the all-must-match filter combination. However transitRadiusM, limit and the role of 'supported research identifier' (businessUbi/parcelNumber) are left unexplained in prose, and parcelNumber's county=King dependency is only in the schema. Adequate but incomplete compensation for the coverage 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?

The description names three concrete resources with their grains: Census housing tenure estimates by ZIP/ZCTA, published Metro boarding stops by coordinate, and OSPI language programs by county, district or schoolCode. That is specific verb+resource detail an agent can act on. It never names the sibling it competes with (e.g. wa_site_context or wa_property_lookup), so routing is left partly to inference.

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 states the input precondition clearly ('Supply a geography, schoolCode or supported research identifier; latitude and longitude must be paired') and the AND-semantics of school filters ('Combined school filters must all match'). It also gives an explicit exclusion set ('Does not determine school attendance, quality, neighborhood suitability or walking time'). No alternative tool is named for overlapping needs, which keeps it short of a 5.

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