Commercial Property Today: CRE market data

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

Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive), and the description adds substantial context beyond them: the two upstream sources, the seasonally-adjusted basis, the series definition (all commercial banks, CRE excluding farmland), and the asymmetric history limits of 12 quarters for Fed versus 5 for FDIC. It stops short of stating units or return ordering, which matters 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?

It is a single sentence with the resource front-loaded and every clause carrying real information (sources, metrics, splits, horizons). The heavy parenthetical nesting makes it denser than ideal, but nothing is 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 one-parameter, read-only, closed-world tool with no output schema, the description is nearly sufficient: it enumerates the returned measures and their coverage windows. Gaps are minor — units of the rates, quarter ordering, and how the Fed and FDIC series are aligned within one response.

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 `quarters` parameter is fully documented in the schema, so the description only needs to reinforce it. It does so by repeating the 12-quarter Fed cap and the 5-quarter FDIC cap, which usefully explains why requesting more than 5 quarters yields mismatched series lengths, but adds no further parameter guidance.

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 (U.S. bank commercial real estate loan credit quality) and enumerates exactly which metrics it carries (Fed delinquency and net charge-off rates, FDIC noncurrent rates by property type), so an agent knows precisely what comes back. It does not explicitly contrast itself with market_snapshot or rate_series, but those siblings are clearly a different resource domain.

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?

There is no statement of when to reach for this tool versus the siblings, no prerequisites, and no exclusions. The usage context is only inferable from the subject matter itself, which leaves the agent to guess whether this is the right call for a general credit-risk question.

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 genuinely new behavioral context: every figure carries a period, release date, stale flag and source link, which tells the agent how to judge data freshness and provenance. It stops short of describing caching, latency or response 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 content is dense and front-loaded: the first clause identifies the source dashboard, then the data inventory, then the per-figure metadata, then the section choice. The long semicolon-delimited inventory is heavy but every item conveys scope; there is little 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 explaining return values, and it does so well by enumerating data families and the per-figure metadata fields. What's missing is the concrete response structure (nesting, units, ordering), so an agent knows what to expect but not exactly how to parse it.

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 enum plus default are fully documented in the schema. The description's 'Pick one section or all' merely restates the section parameter's purpose; it does not map each section value to the specific data groups it contains, which would have been genuinely additive.

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 precisely what the tool returns — a composite market snapshot spanning rates, bank CRE credit, CMBS, prices/cap rates and lending. The enumeration of data sources (Treasury, SOFR, KBRA CMBS, Green Street, CBRE, MBA) makes it clear this is a broad aggregate rather than a single-series reader like the sibling rate_series. It does not explicitly name the siblings, so 4 rather than 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?

The closing line 'Pick one section or all' tells the agent it can scope the call, which is useful usage guidance. However, there is no explicit statement of when to prefer this aggregate over bank_cre_exposure or rate_series, so the choice between siblings is left to inference.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real context beyond that: the data is read from publishers' feeds the site refreshes daily, each series carries a freshness status, and history is bounded. It omits how many series a call can realistically combine with which history depth, which is the only meaningful gap.

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 content is front-loaded — outputs first, then source and the optional history clause — and every clause carries information rather than filler. It is a single dense run-on sentence with heavy parentheticals, which costs a little readability for an agent parsing the boundaries of the series set.

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 explicitly (latest value, observation date, week-ago, month-ago, freshness status). For a read-only, non-open-world tool that is nearly sufficient; the missing piece is the interaction between the 8-series maximum and the 400 series×days cap, which materially limits feasible history requests.

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 and the description must earn more — it does by translating the enum into readable families ("Treasury par curve 1-month to 30-year", "SOFR and its 30/90/180-day averages", "Freddie Mac 30- and 15-year mortgage"). It restates the 1-to-8 series and 365-day bounds but never mentions the series×days cap of 400, so an agent calling with 8 ids and 365 days gets no warning from the prose.

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 its contents (latest value, observation date, week-ago/month-ago readings, freshness status) and enumerates the 19 covered series families in human terms, so an agent knows precisely what data comes back. It falls short of a 5 because it never distinguishes itself from the siblings bank_cre_exposure and market_snapshot, leaving the agent to infer why it should pick this tool over market_snapshot.

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 only implied: the description establishes that this is a read of publisher feeds refreshed daily and that history is optional, which hints at when to reach for it. There is no explicit statement of when to use this instead of market_snapshot or bank_cre_exposure, and no stated prerequisites or exclusions.

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