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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the bar is lower; the description still adds real context by naming the underlying source (HUD's monthly FHA Subsidiary Ledger extract) and clarifying that maturity is a filed source field, not inferred refinance intent. It omits pagination behavior (limit capped at 100, offset up to 10000) and any freshness/latency note about the monthly extract.

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 tight sentences, front-loaded with purpose, then output, then semantics. The enumerated return-field list is slightly long but justified because no output schema exists to carry that 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 9-parameter read tool with no output schema, the description covers the source, the filtering model, the returned fields, and the semantic limits of the data, while annotations handle the safety profile. Only pagination details remain undocumented.

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%, so the description must compensate, and it largely does: it names the optional filter dimensions (state, holder/lender name, unpaid balance, HUD TC/LIHTC) that map to state, lender, min_balance, and lihtc_only. It does not explain matching semantics (exact vs partial lender name) or pagination parameters, leaving limit/offset documented nowhere.

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 ('Find'), a precise resource ('official HUD active multifamily FHA mortgages'), and a scope ('maturing in an exact window') plus the filter dimensions. Negative scoping ('not refinance intent or a contact lead list') separates it from lead-gen/refi-oriented siblings such as affordable_housing_refinance_evidence_pack.

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?

Provides concrete trigger examples ('FHA loans maturing in Texas next year', 'multifamily debt maturity schedule') and one explicit exclusion about what a maturity record does not represent. It stops short of naming an alternative sibling tool or stating when to prefer hud_fha_lender_exposure or hud_lihtc_year15_radar instead.

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