Draw Schedule: multifamily construction financing

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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, so the bar is lower. The description earns credit by disclosing what each comparison row contains – max loan size and rule, rate type, term, coverage test, extra costs, process, and cited regulation or HUD letter – which tells the agent the output's depth and authority.

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 comparison scope, then the per-row content. Dense but every clause conveys distinct information; 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 read-only, single-optional-param comparison tool with no output schema, the description fully specifies the returned fields and their sourcing, so an agent knows exactly what it gets. Nothing needed to invoke correctly 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 description coverage is 100% and the enum values are self-explanatory, so the schema carries parameter meaning. The description adds no format or selection nuance beyond what the schema already says ('omit for all four').

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 ('side-by-side rules for financing') and enumerates the exact four programs compared (HUD 221(d)(4), bank loan, debt fund, 4% LIHTC with bonds). An agent can tell this apart from the sizing and market siblings without opening the 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?

The description makes the comparison use case evident, but it never names the alternatives (size_construction_loan, get_construction_market, get_build_timeline) or states when to pick this tool over them. Usage is implied rather than stated.

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 cover the safety profile: read-only, idempotent, non-destructive, and closed-world. The description adds useful behavioral context beyond that, including the Census source, the ten-year trend, and the connection to HUD upfront MIP and construction interest, though it does not describe exact return shape or limitations of averages.

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 definition is a single front-loaded sentence with no filler, beginning with the data source and core metrics. It is dense but efficient; splitting the HUD/interest clause into a second sentence would improve readability without changing substance.

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 three optional parameters and no output schema, the description is largely complete: it explains the data source, measured durations, dimensions, trend scope, and practical interpretation. It does not describe the response structure in detail, but it gives enough 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?

Schema coverage is 100%, and the schema already documents all three parameters, including defaults and the year-completion meaning. The description reinforces region, building-size categories, and the one-year-plus-trend scope, but adds little parameter semantics beyond what is already structured.

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 data source and resource: Census Survey of Construction averages for apartment buildings, with months from permit to start and start to completion. It also scopes the data by region, building size, completion year, and ten-year trend, making it clearly distinct from sibling tools about market conditions, loan sizing, or construction options.

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 stated content: an agent can infer this is the tool for build-duration questions and HUD MIP/interest context. However, the description does not explicitly say when to use it versus the sibling tools, nor does it state any exclusions or prerequisites.

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 safety is covered; the description adds genuinely new behavioral context about content: seasonally adjusted annual rate, year-ago and pipeline-peak comparisons, the Fed survey quarterly cadence, and 30-day SOFR. It omits freshness/latency and whether the data is cached or live, keeping it below a 5.

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?

One dense but well-ordered sentence: the primary Census series lead, secondary Fed/SOFR sources follow, and the optional parameter closes it. The parenthetical lists carry real information rather than padding, so nothing is wasted.

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 convey what comes back; it does so by enumerating each series and the comparison bases (year-ago, pipeline peak). Only minor gaps remain, such as units/format of the returned values beyond 'annual rate'.

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?

With a single parameter at 100% schema coverage, the schema already defines the 0–60 range and default. The description's 'Optional monthly history' only restates optionality and the quarterly alignment of the Fed series, adding marginal semantics beyond the schema.

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 ('Latest U.S. apartment construction numbers') and enumerates the exact metrics and sources (Census starts/permits/under construction/completions, Fed loan officer survey, SOFR). It does not name or differentiate itself from siblings like compare_construction_options or size_construction_loan, so an agent must infer the split.

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 this is the market-context data source, but never says when to call it versus compare_construction_options, get_build_timeline, or size_construction_loan. No exclusions or prerequisites are given; the agent must infer routing from the topic alone.

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, non-open-world behavior, so the bar is lower. The description adds substantial context beyond annotations: the HUD coverage tests, bank regulatory ceiling, HVCRE equity requirement, optional debt-fund branch, and return fields. It does not cover edge cases or error behavior, but it is well above what annotations alone provide.

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 action and is appropriately sized for a complex three-method sizer. It is a single dense sentence with parentheticals, which is concise but slightly harder to scan than structured sentences.

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 10 parameters, no output schema, and read-only annotations, the description supplies the key calculation methods and return fields (loan, binding limit, equity needed, interest). It is complete enough for invocation, though it lacks sibling differentiation and limitations that would fully resolve when to choose this tool over compare_construction_options.

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 schema already documents all 10 parameters, including defaults and enum meaning. The description adds some conditional context for bank and fund loan-to-cost inputs but largely repeats what the schema already states. Baseline 3 is appropriate when schema does the heavy lifting.

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 verb and resource: it runs a construction loan sizer on a project and enumerates the three sizing approaches. An agent can tell what the tool produces, but the description does not explicitly distinguish it from sibling tools such as compare_construction_options.

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 when the tool applies (sizing a multifamily construction loan three ways) and explains conditional branches for bank and debt-fund loan-to-cost inputs. However, it gives no explicit when-not guidance and does not name alternatives or explain when to use compare_construction_options instead.

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