RentRollAPI

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

Beyond the readOnlyHint annotation, the description discloses that the tool returns a verification report with reconciliation logic, flags uncertain fields, and never silently guesses. It also mentions per-field status/confidence, which adds significant behavioral detail not present in annotations.

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 three dense, information-rich sentences. It front-loads the core purpose, then details the output and verification behavior, and finally covers usage limits. Every sentence earns its place with no redundancy or 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 that there is no output schema, the description fully explains the return value (property info, reporting months, categorized line items, verification report) and key behavioral aspects (status/confidence flags, no silent guessing). It also covers limitations and authentication, making it complete for an agent to decide on invocation.

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 input schema already provides 100% coverage with descriptions for both parameters, including the max size and format detection via fileName. The tool description adds little beyond this, only noting supported formats (PDF, XLSX, CSV) which is already implied by the schema. Baseline 3 is appropriate.

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 ('Extract') and resource ('commercial real estate T12 / operating statement'), clearly distinguishing it from sibling tool extract_rent_roll. It also lists supported formats and the nature of the output, leaving no ambiguity about what the tool does.

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 states the tool is for T12/operating statements, giving clear context for when to use it. It does not explicitly name the sibling tool as an alternative, but the resource type makes the distinction obvious. It also provides usage limits (3 documents/day anonymous) and guidance on how to increase them.

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?

Beyond the readOnlyHint annotation, the description discloses extensive behavior: it returns a deterministic verification report reconciling recomputed totals against stated totals, flags uncertain fields with status/confidence, never guesses, and includes anonymous usage limits (3/day) plus API key authentication via X-Api-Key header. This is rich behavioral context that exceeds annotation coverage.

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 three sentences, front-loaded with the primary purpose, and every sentence earns its place: purpose and scope, output structure and verification behavior, and usage limits/authentication. No redundant or filler content.

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 absence of an output schema, the description provides a comprehensive overview of return values (property info, per-unit records, stated totals, verification report) and behavioral guarantees (status/confidence, flagging uncertain fields). It covers formats, limitations, and authentication. It does not enumerate every output field, but for a 2-parameter tool with no output schema, the description is remarkably complete.

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% for both parameters, and the schema already explains documentBase64 as base64-encoded PDF/XLSX/CSV bytes and fileName as the original name with extension guiding format detection. The description adds mention of scanned documents and size limits but does not meaningfully expand parameter semantics beyond the schema, so 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?

The description clearly states the tool extracts structured, verified data from a rent roll document, specifying the document types (PDF, Excel .xlsx, or CSV; native or scanned). This verb+resource combination is specific and distinguishes it from the sibling tool extract_operating_statement, which targets a different document type.

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 use for rent roll documents and contrasts with the sibling tool by naming the document type, but it does not explicitly state when to use this tool versus extract_operating_statement or provide exclusion criteria. The usage context is clear but not explicitly differentiated.

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