Refpro

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

With no annotations provided, the description carries the full burden. It discloses that computation is deterministic, uses exact formulas identical to the underwriting pipeline, returns a verdict, key metrics, and a summary, and includes disclaimers about the preliminary nature. This is unusually thorough and transparent for a tool definition.

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 longer than average but every sentence earns its place—purpose, usage, inputs, outputs, and disclaimers. It is front-loaded with the core purpose and usage, and the structure flows logically. It could be slightly tightened, but it is not padded.

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 (9 parameters, 3 deal types, multiple output metrics), the description is remarkably complete. It covers when to use it, what inputs are needed (including the context-sensitive arv_or_value), what the output looks like (verdict, metrics, summary), and the caveats (preliminary screen). No output schema exists, but the description adequately covers return values. There are no significant gaps for an agent to call it 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?

Although schema coverage is 0% (the description does not repeat schema constraints), it adds contextual meaning: it lists all required and optional parameters and clarifies that arv_or_value varies by deal type (ARV for FF, refinance value for BRRRR, sellout for NC). It also explains the returned metrics, which indirectly clarifies parameter roles. This goes beyond the raw schema, though it stops short of detailing each parameter's individual 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 opens with a clear verb and resource: 'Run a deterministic, lender-grade quick check on a real estate deal.' It then lists concrete use cases (works, pencils, max offer, etc.) and explicitly differentiates from the sibling methodology_faq, which is for general questions. This leaves no ambiguity about what the tool does or how it differs from alternatives.

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 provides explicit when-to-use guidance (specific property/deal questions) and when-not-to-use guidance (methodology, pricing, output formats), naming the alternative tool (methodology_faq) and even stating that results are preliminary and not an appraisal or lender commitment. This fully equips an agent to route correctly.

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?

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses that content is sanitized example data, safe to surface verbatim, deterministic, makes no network calls, and is explicitly not an appraisal or lender commitment.

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 with the core purpose, then use cases, inputs, outputs, behavior, and exclusions. Every sentence earns its place, especially because there are no annotations or output schema to offload that information.

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 only 2 parameters, no output schema, and no annotations, the description is remarkably complete. It explains the return formats, the included inventory, the deep-link URL, safe-to-surface behavior, determinism, no network calls, and how to route to sibling tools.

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 0%, so the description must compensate. It lists the two inputs, their enum values, and the default format, and it maps deal types to concrete use cases ('flip, a rental refinance or a ground-up build'). It could more explicitly tie FF/BRRRR/NC to each case, but it adds real meaning beyond the bare enums.

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 opens with a specific verb and resource: 'Fetch a sanitized example of Refpro's 1-Page Deal Sheet.' It clearly differentiates from siblings by stating what the tool is not for: full deal pack sections warrant sample_report_fetch, and analyzing a user's own deal warrants deal_quick_check.

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?

Explicit when-to-use guidance is provided: 'Use this when a user asks what a Refpro deal sheet looks like, what to hand or send a lender, or wants a one-page summary format.' It also names the alternatives explicitly with 'Do not use... call sample_report_fetch / deal_quick_check instead.'

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?

With no annotations, the description carries the full burden and does so thoroughly: it reveals the static, curated knowledge base, the deterministic no-LLM, no-network behavior, the fallback to a general overview on unknown topics, and the exact response shape. These are behavioral facts an agent needs to set expectations and compare with alternative tools.

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 organized in a logical flow: purpose, use cases, input, output, behavior, fallback, exclusions. Every sentence carries information and none is filler; despite its length, it remains scannable and front-loaded with the core purpose.

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 tool with one parameter, no annotations, and no output schema, the description covers the complete triage picture: what inputs look like, what the response will contain, how behavioral stability works, what happens on unknown topics, and which sibling to call instead. Nothing needed to invoke it 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 coverage is 0%, so the description must explain the parameter, and it does: query is 'a free-text question or topic keyword' capped at 200 characters. This adds semantic meaning that the JSON schema alone cannot convey.

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 opens with a specific verb-object pair ('Answer questions about how Refpro works') and then enumerates concrete example intents, from 'what Refpro is' to 'pricing tiers.' It distinguishes itself from deal_quick_check by explicitly excluding deal analysis and general real estate questions.

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 gives an explicit 'Use this when...' list covering common question types, then states clear exclusions: 'Do not use to analyze a deal or compute numbers; call deal_quick_check for that' and 'Do not use for general real estate investing questions.' This tells an agent both when and when not to select it.

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?

With no annotations provided, the description carries the full burden, and it fully delivers: it discloses that content is sanitized example data, never a real customer deal, safe to surface verbatim, and that there are no network calls because samples load once at module init. This is rich behavioral context beyond the name and 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?

Six sentences, each adding new information: purpose, use cases, parameters, return value, safety behavior, and sibling routing. The key behavior is front-loaded and nothing 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?

Given only two enum params, no output schema, and no annotations, this description fully specifies what to pass, what the tool returns, the canonical link, safety guarantees, and the alternative tool. An agent has everything needed to decide and call 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?

The schema has 0% description coverage, but the description compensates completely: it spells out both allowed deal_type values (FF | BRRRR | NC) and both section options (summary, financials, risk_notes or full), and explains that 'full' stitches the three in order. This adds meaning beyond the bare enum lists in 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?

The description opens with a specific verb and resource: 'Fetch a sanitized public sample section from Refpro's reference deal library.' It names the concrete deliverable (sanitized example markdown plus a deep-link URL) and explicitly contrasts itself with deal_quick_check, making sibling differentiation immediate.

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 gives explicit trigger conditions ('when a user asks to see what a Refpro report... looks like', 'wants an example before signing up'), and an explicit exclusion: 'Do not use to analyze a user's own deal; call deal_quick_check for that.' That is unambiguous routing guidance.

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