cmbs.loan: CMBS loan rates, lenders and servicing

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

Annotations already establish read-only, idempotent, non-destructive, and closed-world behavior. The description adds meaningful behavioral context beyond that: the actual formula, the returned components, and the 25% deemed reduction when no appraisal arrives, though it does not discuss edge cases or exact output shape.

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 but front-loaded: it states the purpose, gives the formula, and lists the return components without filler. Every sentence contributes useful information for invoking the tool.

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 six-parameter calculator with no output schema, it supplies the needed formula, domain context, and high-level return values. It still lacks exact output field names, precision, and edge-case behavior, so it is not fully complete.

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?

All six parameters have 100% schema description coverage, so the baseline is 3. The description improves on that by mapping the inputs into the appraisal reduction formula, though its parenthetical phrasing around unpaid interest, advances, and other amounts due is not fully unambiguous.

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 calculation and resource: the CMBS appraisal reduction amount for a delinquent loan using a new appraisal and a defined PSA formula. This is clearly distinct from the sibling tools, which are lookups, estimators, and loan sizing utilities.

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 clear context for use: a delinquent CMBS loan, a new appraisal, and a 2025 pooling and servicing agreement formula. It does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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 declare readOnlyHint/idempotent/non-destructive, so the bar is lower, and the description adds real context: the fee terms source (a 2025 PSA), rates and minimums, and what gets returned. It could still say whether inputs are validated or how the outcome enum gates optional parameters, but the disclosure is strong.

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 core purpose and the fee terms, then closes with the return shape. It is dense but every clause earns its place; slight density in the fee-rate enumeration keeps it from a 5.

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 6 parameters and conditional-required fields all documented in the schema, and no output schema, the description supplies the return-value summary and the fee model needed to interpret results. An agent has enough to call it correctly; minor gap is that it doesn't restate which optional inputs pair with which outcome.

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% and each parameter already has a descriptive note including conditional requirements (proceeds for payoff, note_rate/months_to_maturity for corrected). The description adds no parameter-level detail beyond the outcome naming, so baseline 3 applies.

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 (estimate) and resource (special servicing/workout/liquidation fees) and enumerates the three outcome branches the tool models. Clearly differentiable from siblings like special_servicing_timeline, which covers timing rather than fee math.

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 three-outcome framing (corrected, refi120, payoff) implicitly tells the agent when each computation applies, and the description makes clear this is a fee-estimation tool for a single outcome. It does not explicitly name a sibling or state exclusions, so it falls short of a full 5.

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 declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds real value beyond that: the ranking methodology, the SEC-filing source of truth, and the pagination-per-lender behavior ('a page per lender').

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 purpose front-loaded and zero filler. The first sentence is information-heavy but every clause (ranking, window, source) earns its place.

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 compensates by enumerating return fields (volume, loan count, size range, median rate, leverage). For a 4-param read-only filter tool this is nearly complete, though default limit behavior is left to the schema.

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 earns above that by clarifying the non-obvious semantics of loan_amount as a spanning filter rather than an exact match, and by signaling that property_type/state are optional limiters.

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 ('CMBS originators ranked by loan volume') plus the data provenance (originator named in trusts' SEC filings) and time window. An agent can clearly distinguish this ranked-list tool from the singular get_cmbs_lender sibling without opening a 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?

Explains what each filter does, including the subtle 'keeps lenders whose securitized loan sizes span it' semantics for loan_amount, which tells the agent when that filter is appropriate. It stops short of explicitly routing between siblings like get_cmbs_lender or size_cmbs_loan, but the usage context is clear.

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 declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds real value beyond that by disclosing the data provenance (SEC filings) and the exact metric set returned, which the agent cannot get elsewhere since there is no output schema.

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 identity and source of the dataset before the field enumeration. The long metric list is justified because no output schema exists, though it could be grouped slightly more tightly.

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 correctly compensates by listing the returned fields (volume windows, loan sizes, median rate, leverage, property types, states, recent loans). The remaining gap is failure behavior for an unrecognized lender and the discovery path to a valid slug.

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 the single parameter is already documented with examples, so the schema carries the burden. The description's examples ("Citi", "wells-fargo") reinforce that slugs are hyphenated lowercase, but add little beyond the schema's own examples.

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 and resource ("One CMBS originator's securitized book from SEC filings") and enumerates the returned metrics, so an agent knows exactly what it gets. It is distinguishable from find_cmbs_lenders by the singular "one lender" framing, though it never names that sibling to make the contrast explicit.

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?

"Give the lender's name or slug" implies the caller must already know a valid lender identifier, which hints that a lookup step may precede this call. But there is no explicit routing to find_cmbs_lenders for discovery, and no statement of what happens when the lender is unknown or ambiguous.

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 declare readOnly, idempotent, closed-world behavior, so the bar is lower; the description adds real value by defining the refinance-gap proxy (NOI at securitization under 9% of today's balance) and the filter-exclusivity constraint, which are not in annotations. It does not describe result ordering or size.

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?

A single front-loaded sentence that leads with the resource and maturity-year grouping before the derivative detail. Dense with parentheticals but every clause (metric list, proxy definition, filter rule) earns its place.

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?

No output schema exists, yet the description enumerates all returned measures and the three grouping modes (overall, property type, state), which is exactly what an agent needs to interpret results. Nothing material is missing for a two-optional-parameter read-only aggregate.

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 a 3 is the baseline; the description earns above that by stating the mutually-exclusive filter constraint and confirming that omitting filters yields the overall view, semantics the schema itself does not encode.

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+resource ('CMBS loans still reporting, by maturity year') and enumerates the exact measures produced (count, balance, average note rate, share with NOI below 9% of balance, comparison to median new-loan rate). This is clearly an aggregate maturity-wall analysis, distinguishable from sibling tools like get_cmbs_rates or find_cmbs_lenders.

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?

Explains the available filtering modes ('Overall, by property type or by state') and adds the operative constraint 'one filter at a time,' which tells the agent how to call it. It does not explicitly say when to prefer this over get_cmbs_rates or get_cmbs_underwriting, so no exclusion guidance.

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 declare readOnlyHint, idempotentHint, non-destructive behavior, and closed-world scope. The description adds meaningful context beyond that: SEC Form ABS-EE as the source, closed-loan basis, securitization windows, and included statistics such as the middle half, loan counts, and 5- vs 10-year split.

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 two sentences, front-loads the metric and scope, and each clause adds relevant scope or output detail. 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?

Given the rich annotations, absent output schema, and fully documented single optional parameter, the description provides enough source, scope, and return-content detail for an agent to invoke the tool correctly.

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?

There is one optional enum parameter with 100% schema description coverage, so the schema already explains the property_type values and that omission means all types. The description mirrors 'overall or for one property type' but adds no new syntax or default semantics.

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 states a precise resource and scope: median original note rates on CMBS loans securitized over 90 days, 180 days, and 12 months, optionally by property type. It is clear enough to separate from rate-unrelated siblings, but it does not explicitly position itself against tools like get_cmbs_underwriting or get_cmbs_maturity_wall.

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?

Usage is implied by the context of current CMBS rates, and the description adds a useful caveat that these are rates on closed loans rather than a quote. However, it gives no explicit when-to-use guidance or alternatives among the sibling tools.

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 declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds useful context beyond them: the SEC loan-data provenance, the historical window, and that figures are aggregate medians/percentiles rather than individual loans.

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?

A single front-loaded sentence that names the data and source before the metric list. It is dense—the metric list is long—but every clause carries information, with 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?

With only one optional parameter and no output schema, the description carries the burden of describing returns, and it enumerates the return metrics thoroughly. It stops short of describing result shape (e.g., how percentiles are presented, sample counts), which leaves a small gap.

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?

One optional parameter with 100% schema description coverage and a full enum, so the schema already does the work. The description's 'overall or for one property type' merely restates the omit-for-all behavior the schema documents; no extra syntax or filtering nuance is added.

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 concretely what the tool returns (underwritten loan size, LTV, DSCR, debt yield, occupancy medians/percentiles, IO share, term mix) and the data source and window (SEC loan data, last 12 months). This clearly distinguishes it from siblings like get_cmbs_rates, get_cmbs_maturity_wall and size_cmbs_loan, which cover different resources.

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 'what lenders actually underwrote' framing plus the trailing-12-month window tells the agent this is for observed market benchmark data, not forward-looking quoting or single-loan sizing. It never names an alternative tool or an exclusion, so routing is implied rather than explicit.

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 that this is a read-only, idempotent, non-destructive, closed-world operation. The description adds meaningful behavioral context beyond that: it explains the three sizing tests, states which test binds, and documents default assumptions for omitted limits and the rate.

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 but front-loaded: it first states the core result, then explains the three tests and default assumptions. Every sentence carries useful information for a complex sizing tool, with 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?

Given the tool's complexity, rich schema, and annotations, the description is largely complete. It explains the calculation logic and defaults, though without an output schema it could more explicitly describe the full return shape beyond the maximum loan and binding test.

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%, so the baseline is 3. The description still adds value by explaining that omitted limits default to recent CMBS percentile assumptions by property type and that the rate defaults to the 90-day median, which is not fully captured in the schema descriptions.

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 states a specific verb and resource: sizing the maximum CMBS loan on a property. It also names the three lender sizing tests and says the result identifies which test binds, which is enough to distinguish it from sibling tools like get_cmbs_rates or get_cmbs_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 the tool is used to size a CMBS loan, but it does not explicitly say when to use it versus alternatives such as get_cmbs_underwriting or get_cmbs_rates. There are no exclusions or routing instructions, so usage is only implied.

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 declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds real context beyond that: the sequence is contractual and day-by-day, each event carries its PSA section, and passing days_elapsed shifts the output from a full schedule to a triggered/pending split with days remaining.

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 scenario that activates the tool and then the mode-switching instruction. The middle clause stacks four enumerated events, making the first sentence dense, but no sentence is 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?

With no output schema, the description carries the burden of describing returns and does so: a day-by-day event sequence with PSA sections, plus triggered/next-event status when days_elapsed is given. What it leaves unstated is the concrete output shape (e.g., whether events come back as a dated list), which is a minor residual gap for a two-parameter reference tool.

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, but the description adds meaning the schema lacks: it explains that days_elapsed determines which events are already triggered and surfaces the next one with days remaining, which is return-shaping semantics rather than a restatement. The trigger parameter itself is only implied by 'after a missed monthly payment or a missed balloon,' relying on the schema for its enum values.

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 (the CMBS special servicing timeline) and enumerates its contents: transfer to special servicer, SEC delinquency codes, appraisal reduction trigger, and the 120-day maturity window. Nothing in the sibling list (fee estimators, lender lookups, rate and underwriting tools) overlaps with this reference-sequence function, so the agent can route here without ambiguity.

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?

It states the triggering condition clearly (after a missed monthly payment or missed balloon) and explains the two modes of use: omit days_elapsed for the full sequence, supply it to get triggered events. It does not name sibling alternatives or exclusions, but the sibling set is functionally disjoint enough that this costs little.

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