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

Annotations already declare readOnly/idempotent/openWorld=false, but the description adds substantial uncovered behavior: the entitlement model (first 5 rows plus locked.count/locked.by_type, never full rows; contact values and decision-maker names withheld), the coverage boundary (conduit originators only; balance-sheet, debt funds, life companies absent), and how thin local markets fall back to national comparables.

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 purpose and routing guidance, and almost every clause carries operational value. It is dense and runs long (entitlement detail plus a trailing promotional plan link), which costs a point on tightness, but nothing essential is buried.

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?

With no output schema, the description explains the row shape in detail (lender name normalised to parent, local/national counts and balances, latest origination, three example loans with property/city/trust/filing). Combined with access limits, coverage gaps and alternatives, an agent has everything needed to call it and interpret the result.

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 89%, so the schema already does most of the work and the baseline is 3. The description adds the interpretation layer the schema does not: the ranking factors (property type, states/city, size band, recency and size fit) and the band-vs-comparable-size framing that gives meaning to band_min/max versus size_min/max.

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?

Names a specific verb+resource: lenders ranked on the commercial real estate loans they ORIGINATED, sourced from CMBS loan-level SEC ABS-EE filings. It explicitly distinguishes itself from the closest sibling (find_lenders_for_financing) and states its scope restriction to conduit originators.

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 concrete when-to-use query examples ('find lenders for a $100M hotel in Atlanta'), an explicit exclusion ('use it, never find_lenders_for_financing, whose comparables are corporate BDC loans'), and a complementary sibling ('pair it with search_bank_cre_exposure for local banks'). When-not and alternatives are both covered with the reason why.

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