CRE Capital: capital stack calculator

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add semantics — and it does: omitted rates fall back to the 10-year Treasury plus Altus Q2 2026 average quotes, and results are arithmetic on the inputs rather than a quote or projection. It does not discuss validation failures or what happens at boundary inputs, but the default-derivation disclosure is genuinely useful.

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 core action and layer list, followed by the default policy and the 'not a quote' disclaimer. The long output-metric enumeration in sentence one is dense but justified since there is no output schema.

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 18 parameters and no output schema, the description carries return-value explanation and does so thoroughly (per-layer amounts, LTV/LTC, DSCR, IRRs, cash flows). Combined with the 100%-covered schema, an agent has nearly everything needed; only guidance on choosing this over the sibling cost/provider tools is absent.

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%, with per-parameter descriptions already carrying the default rules (e.g. senior rate = Treasury + 195 bp) and ranges. The description only restates the general default policy, adding no parameter-level detail beyond what the schema provides, so the 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 and resource ('Runs the cre.capital stack builder on a deal') and enumerates the layers constructed: senior loan, mezzanine, preferred equity, common equity, optional JV split. This clearly separates it as a computation tool rather than a lookup, though no sibling tool is named to reinforce the distinction.

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 rather than stated: the tool is a calculator that fills in missing rates from Treasury plus Altus Q2 2026 quotes. There is no explicit 'use this when...' or 'prefer get_capital_costs for...' guidance, so the agent must infer the split from siblings on its own.

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 this is a safe, read-only, idempotent, closed-world read, so the description spends its words on what annotations cannot convey: data provenance (Altus Group averages, public REIT 10-Q disclosures), the specific quarter, the quoting convention (spreads over 5-/10-year Treasury or Term SOFR, by LTV band), and the presence of the current benchmark rate. That is exactly the extra context an agent needs to trust and interpret the numbers.

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?

It leads with the purpose and every clause carries substantive information about contents or sourcing rather than filler. The single elaborate sentence is somewhat run-on and could be split for scanability, which keeps it below 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 no output schema, the description carries the burden of describing what comes back, and it does: fixed and floating lender quotes by LTV band, the current 10-year Treasury, implied all-in senior and mezzanine rates, and REIT-reported earnings per layer. An agent knows what it will receive and for which period.

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 the single `layer` enum is fully described in the schema, so the description's 'Filter by layer' adds no meaning beyond it. Baseline 3 applies when the schema does all the parameter work.

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 the exact resource and scope: cost of senior debt, mezzanine and preferred equity, sourced from Altus Group Q2 2026 quotes and REIT 10-Qs. It is unmistakably a pricing/cost tool, which implicitly separates it from `capital_stack` (structure) and `list_capital_providers` (providers), but it never names those siblings to make the distinction 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?

The only usage instruction is the closing 'Filter by layer,' which restates the parameter rather than guiding tool selection. There is no statement of when to reach for this versus `capital_stack` or `list_capital_providers`, and no prerequisites or exclusions.

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?

The annotations already establish that this is a read-only, idempotent, non-destructive, closed-world lookup. The description adds useful behavioral context by stating the data is limited to what institutions publish and that list membership does not guarantee deal participation, though it does not mention pagination or exact return 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 front-loaded with the core resource definition and follows with filtering and caveat information. It is dense but every sentence contributes; minor redundancy with the fully documented schema keeps it from being maximally concise.

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 simple two-parameter lookup with rich annotations and no output schema, the description covers the resource, data provenance, filtering, and a key limitation. It could be slightly more complete by specifying the return structure or ordering, but nothing essential 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 100%, so the baseline is 3. The description goes further by explaining what the list categories represent and clarifying that the name filter matches only part of a firm name, adding meaning beyond the enum and 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 uses a specific verb and resource: it returns firm names for each capital-stack layer, sourced from named institutional lists. It clearly distinguishes this from the sibling capital_stack and get_capital_costs tools by focusing on provider identity rather than stack structure or pricing.

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 how to use the filters (by list or by part of a name) and adds an important caveat that inclusion does not imply a firm will quote a given deal. It does not explicitly compare when to use this tool versus capital_stack or get_capital_costs, so it falls short of full alternative guidance.

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