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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description adds substantial non-redundant behaviour: a single annual capture dated 2025-12-31, the meaning of NULL waiting lists as absent disclosure rather than empty queues, the fact that min_waiting_months drops those rows, and the clarification that occupancy is measured against available (not built) units.

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?

Long but front-loaded and dense: the resource, row shape and field list come first, then filters, then the crucial snapshot/NULL caveats. Nearly every clause carries a distinct fact; only minor phrasing is padded.

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 an 8-parameter tool with no output schema, the description supplies the return fields, the canonical dfx_id join key, the ordering, the snapshot caveat, and the NULL-disclosure behaviour, plus how the answer reports nearby reporting projects. No output schema is needed given this coverage.

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 100% so the schema baseline is 3; the description adds interpretive value beyond it, notably the 'mean' of an occupancy figure (100% of 20 available can be 20 of 50 built) and the consequence of a NULL waiting list for min_waiting_months. It doesn't document every parameter's syntax, so it is an enrichment rather than a replacement.

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 (search) and a precise resource (HUD project-level Picture of Subsidized Households), enumerated with row granularity (one row per project and programme), scope (29,455 projects nationally), and the exact return fields. It is unmistakably distinct from every sibling in the list, none of which touch subsidised housing.

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 clear operative context: the legal filters (state, city, programme, waiting list, occupancy, units), the sort order, and the free/snapshot nature. It also warns which rows the answer excludes and how the answer compensates. It stops short of naming an alternative tool or an explicit when-not-to-use, so it does not reach 5.

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