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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description is free to add higher-value context — and it does: the two source sets are not silently property-matched because FHA's workbook lacks a street-address key, and results make no refinance/contact/valuation/affordability-expiration claims. That is unusually candid about analytical limitations and non-claims.

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?

Two dense sentences with the deliverable front-loaded and the caveats second; nothing is filler. Slightly heavy clause packing, but every clause carries distinct 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 five-parameter, no-output-schema composite tool, the description covers scope, source composition, and explicit non-claims. It leaves pagination/limit behavior and the shape of the returned pack unstated, but the core decision inputs are present.

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 60% (start_date, end_date, response_format documented; state and limit bare). The description reinforces the state-level and date-window framing but adds no syntax, default, or meaning for the undocumented 'limit' parameter or any new detail beyond the schema. Baseline 3 fits.

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 composite resource ('return a source-linked, state-level evidence pack') and names both underlying source sets (HUD FHA maturity records, HUD LIHTC year-15 signals) plus the scope (one date window). An agent can distinguish this composite pack from the sibling single-source tools hud_fha_maturity_search and hud_lihtc_year15_radar without opening the schema.

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?

'Use this for affordable-housing debt or timing diligence' gives an intended use case, which is more than nothing. However it never names the narrower siblings (hud_fha_maturity_search, hud_lihtc_year15_radar) or states when to prefer them over this combined pack, so the routing decision is left implicit.

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