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

Annotations only cover the read-only/idempotent safety profile, and the description goes well beyond that: it discloses the entitlement model (first 5 rows in full, locked.count/locked.by_type, contact values and decision-maker names withheld), the `entitlement`/`locked` response fields, and the critical semantic that a zero realized loss is stored as absent so 'not reported' is never 'no loss'. That is exactly the kind of non-obvious behavior an agent cannot infer from structured fields.

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?

Front-loaded with the resource and scope, and the returned-field list and access caveats are all load-bearing. The closing pricing/CTA sentence ('Full access: DFX Intelligence, 7 days free at ...') is promotional rather than operational, which slightly dilutes an otherwise dense, well-ordered description.

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?

There is no output schema, so the description must carry the return contract, and it does: it enumerates the per-loan fields, mentions the aggregate summary by resolution and total reported loss, notes pagination via next_cursor, and documents the degraded-entitlement response shape. Nothing an agent needs to call or interpret results is missing.

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 75% and the description adds meaning the schema lacks: it decodes the liquidation codes that the `resolution` filter matches ('disposition/liquidation, discounted payoff, payoff, repurchase') and clarifies that loss/severity figures are 'last reported realized losses'. It adds less for limit/cursor/state, but those are self-evident or already documented.

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 precise verb and resource ('every conduit CMBS loan whose servicer reported a foreclosure, REO or deed in lieu workout') with the source (SEC ABS-EE) and enumerates the returned attributes. It explicitly disambiguates from the sibling search_cmbs_loans, so an agent can pick correctly without opening either 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?

Names the alternative explicitly ('For live loans and their current status use search_cmbs_loans') and gives the selecting condition. The description also frames the tool as the answer to a specific question ('which CMBS loans went to foreclosure and how were they resolved'), which is a clear use trigger.

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