refpro-mcp

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

With no annotations, the description carries the full burden and compensates well: it discloses determinism, precision ('no estimates, no rounding shortcuts'), and the exact nature of outputs per deal type. It doesn't discuss side effects or error handling, but for a calculation tool, the disclosed traits provide solid transparency.

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 a single dense sentence that efficiently packs purpose, inputs, outputs, and quality guarantees. Every clause earns its place; no redundancy or fluff. It is front-loaded with the core purpose and flows logically.

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 9 parameters, no output schema, and no annotations, the description covers required and optional inputs, explains the output structure (verdict, metrics per deal type, summary), and gives a quality benchmark. It could mention why zip_code is required or how errors are surfaced, but the provided information forms a complete enough mental model.

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 description adds essential meaning beyond the bare schema by explaining arv_or_value varies by deal type (ARV for FF, refinance value for BRRRR, sellout for NC) and marking optional parameters. Since the schema has no parameter descriptions, this compensates significantly, though not every parameter (e.g., annual_debt_service) is explicitly explained.

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 clearly states the tool runs a 'deterministic, lender-grade quick check' on real-estate deals, lists the deal types (FF, BRRRR, NC), and details the output (verdict, metrics, summary). This distinguishes it from siblings (methodology_faq, sample_report_fetch) which serve entirely different purposes.

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 context by contrasting with the 'full deal pack' and emphasizing 'quick check', implying it's for rapid assessment rather than full underwriting. However, it doesn't explicitly state when to use this tool versus siblings or mention exclusions, 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?

It reveals multiple behavioral traits: static curated knowledge base, no LLM-generated answers, no network calls, fallback behavior, and exact return format (answer length, related topic list, source URL). This significantly exceeds what annotations would 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 four sentences, each conveying essential information: purpose, knowledge base nature, output structure, and fallback. It is front-loaded with the primary purpose and remains readable.

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 simple one-parameter schema and no output schema, the description covers all essential aspects: what it does, how it behaves, what it returns, and fallback behavior. It is sufficiently complete for an agent to use 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 a single 'query' parameter with no enum and no description. The tool description indirectly defines the query by listing the topics it can answer (methodology, deal types, pricing, etc.), which helps the agent construct a relevant query, but it does not explicitly explain the parameter's format or provide 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?

The description clearly states the tool answers structured questions about Refpro's methodology and lists specific topics (deal types, pricing, output formats, etc.), making the purpose distinct. However, it does not explicitly contrast with sibling tools, so it doesn't fully achieve sibling differentiation.

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 for methodology questions but provides no explicit guidance on when to use it vs deal_quick_check or sample_report_fetch, nor does it mention exclusions or alternatives.

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 fully discloses key behavioral traits: no network calls, samples loaded once at module init, content is sanitized and safe, and the 'full' section stitches other sections in order. This goes well beyond what the schema or annotations provide, giving the agent a complete understanding of side effects and return behavior.

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 concise and well-structured, with each sentence earning its place: purpose, inputs, return value, special case ('full'), safety, and performance. It avoids redundancy and front-loads the primary 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?

Given the tool's simplicity (2 parameters, no output schema), the description covers all necessary context: what it returns (markdown content and deep-link URL), the nature of the data (sanitized example), and operational details (no network calls). It is complete for an agent to select and 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 description coverage is 0%, so the description compensates fully by listing exact enum values for deal_type (FF, BRRRR, NC) and section (summary, financials, risk_notes, full). It also explains the meaning of the 'full' section, adding value beyond the schema's bare enum definitions.

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 clearly identifies the tool's action with a specific verb ('Fetch') and resource ('sanitized public sample section from Refpro's reference deal library'). It distinguishes itself from sibling tools by focusing on retrieving sample sections, whereas deal_quick_check and methodology_faq appear to serve different purposes.

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 clear context on when to use the tool: it returns sanitized example data that is 'safe to surface verbatim to end users.' It also implies when not to use it by stating 'not a real customer deal.' However, it does not explicitly mention alternatives or contrast with sibling tools, 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.