Conduit.loans: CMBS conduit loan sizer

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

Annotations already establish read-only, idempotent, closed-world behavior, so the description's job is additive — and it adds real context: data provenance (the trusts' own SEC ABS-EE filings), a freshness window (last 12 months), and the fact the cuts are mutually exclusive. It still doesn't disclose limits such as minimum loan counts, latency, or sample-size caveats.

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 sentences, front-loaded with the metrics and universe before the slicing rules; every clause carries information. The parenthetical metric list and nesting make it dense to parse, but there is no filler.

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 three-optional-param analytics tool with full annotation and schema coverage and no output schema, the description supplies the metric set, source, and slicing semantics an agent needs to select and call it. Missing only richer guidance on output shape granularity and any sample-size constraints.

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% and both enums are documented, so the baseline is 3. The description adds a little beyond the schema by explaining the no-parameter default yields the whole market plus a median line, but it adds nothing about include_trusts or the mutual-exclusivity mechanics beyond what the schema already states.

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?

The description names a specific resource and metric set (DSCR, LTV, debt yield, coupon percentiles, full-term IO share) over a defined universe (CMBS conduit loans originated in the last 12 months) and a named data source (trusts' SEC ABS-EE filings). An agent knows this is a market-aggregate underwriting-stats tool, not a single-loan tool. It does not explicitly contrast with the sibling size_conduit_loan, so it stops short of a 5.

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?

'Cut by property type or by loan term (5 or 10 years); with neither, the whole market plus a median line' gives concrete guidance on how slicing the query changes the result. There is no explicit 'use this instead of X' routing versus size_conduit_loan and no stated exclusions, which keeps it at 4.

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

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful context: defaults come from recent conduit underwriting edges and median coupons, those defaults can be overridden, and the result identifies which constraint binds along with debt service and ratios.

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?

The description is dense and front-loaded with the core operation. It is a single long sentence, but most of the information is useful rather than redundant.

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 nine-parameter financial calculator with no output schema, the description adequately covers the operation, the tests, the output summary and default behavior. Minor gaps remain around assumptions and edge-case handling, but the critical information is 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 100%, so the baseline is 3. The description adds rationale for the defaulted DSCR, LTV, debt-yield and rate parameters by explaining their provenance and overrideability, which goes beyond the schema's field-level default notes.

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 resource: sizing a maximum CMBS conduit loan from NOI and value, and names the tests it runs. It is clear, but it does not explicitly distinguish itself from the sibling tool current_underwriting.

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?

The description implies usage through defaults and override behavior, and notes that omitting value skips the LTV test. It does not say when to use this tool versus current_underwriting or state any exclusions.

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