Razi Document Tools

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

The description is highly transparent about lossy compression, no quality knob, non-guaranteed compression, fallback to original bytes, and the lack of an upload channel. It loses a point because the mention of passing 'fileUrl' conflicts with the empty input 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?

The description is front-loaded with the main purpose and is dense with useful details. It is somewhat long, but each sentence provides relevant operational context, so it remains reasonably concise.

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?

The description covers fallback behavior, limitations, alternatives, rate limits, and processing time, which is strong contextual coverage. It is not fully complete because the input schema is empty while the description implies a required fileUrl argument.

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 references a 'fileUrl' parameter and says 'pass fileUrl', but the input schema declares no properties and no required fields. This is a meaningful mismatch: the description adds parameter information that the schema does not support.

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 compresses PDFs: 'Shrink a PDF's byte size while keeping it a PDF'. It is distinct from sibling tools like extract_text_ocr, merge_pdf, parse_document, and split_pdf.

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 usage guidance: 'This is for PDFs only — use compress_image for images and compress_video for video.' It also notes rate limits, paid compute, and fallback behavior, leaving little ambiguity about when to use 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?

No annotations provided, so description carries full burden. It discloses limitations (misreads under blur/skew/low contrast), output format behavior (flat string, layout not preserved), rate limit (20 calls/hour/IP), and access constraints (no upload channel, URL must be in razi.pro storage). Rich behavioral disclosure.

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?

Every sentence adds value. The description is dense but well-organized: purpose, comparison, limitations, and usage constraints. No fluff or redundancy.

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?

Covers purpose, alternatives, input requirements, output shape (JSON with text/language/confidence), and constraints. Despite no output schema, the description gives enough context for correct 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?

Schema covers 100% of the single parameter with a description, but the tool description adds significant meaning: ISO 639-2 style code, default eng, one language per call, and accuracy impact of wrong language. Goes well beyond the schema basics.

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 ('read text off an IMAGE'), resource (image), and method (OCR), and explicitly contrasts with parse_document. Clear and distinguishes from siblings.

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?

Explicitly tells when to use this tool vs parse_document based on content type (pixels vs text) and even recommends preferring parse_document for text-bearing files. No ambiguity.

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?

No annotations are provided, so the description carries the full burden, and it delivers: page content is copied unchanged, fewer than two files are rejected, third-party URLs are rejected, MCP has no upload channel, and there is a rate limit. These are behavioral facts an agent cannot infer from the schema or name.

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 long but every sentence earns its place, and the core behavior is front-loaded. It packs scope, alternatives, input constraints, security restrictions, API differences, and rate limits without redundancy.

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 there is no output schema and no annotations, the description covers all critical operational context: input form, ordering, copy behavior, exclusions, storage URL requirement, API channel difference, and quota. An agent has enough to decide whether and how to invoke this tool, with the only caveat being that the parameter is documented in prose rather than in the schema.

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 is empty, so the description is the only source of parameter meaning. It clearly specifies `fileUrls` as an array of URLs in razi.pro's own storage, gives an example source (`url` returned by upload_file), and states that third-party URLs are rejected. This more than compensates for the empty schema, although the schema/description mismatch itself is notable.

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 sharp verb-object pair: 'Concatenate two or more PDFs into a single PDF, in the order supplied.' It also explicitly distinguishes itself from compress_pdf and split_pdf, so an agent can tell exactly what this tool does and what it does not do.

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 when-to-use, when-not-to-use, and alternatives: 'it does not compress (use compress_pdf) or select pages (use split_pdf)' and 'for a mix of images and PDFs use images_to_pdf.' It also states hard rejection conditions, URL requirements, and the 20-merges-per-hour rate limit, giving the agent enough guidance to avoid invalid calls.

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 covers key behaviors: accepted file types, rejection with 400 for unsupported extensions, UTF-8 decoding, extension-based type detection rather than content sniffing, and the lack of an upload channel. It also discloses the rate limit and third-party URL rejection.

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 somewhat long but each sentence adds distinct, essential information about behavior, limits, or alternatives. There is minor redundancy (e.g., stating .txt-only support and then mentioning PDF parsing is not implemented), but no filler or irrelevant 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 tool's limited scope and sibling context, the description is near-complete: it defines output, error behavior, file-type detection, URL requirements, rate limits, and the relationship to extract_text_ocr. An agent has enough context to select and invoke the tool correctly without additional documentation.

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 declares no parameters, so the description is the only source of parameter information. It names `fileUrl` and explains its expected format and constraints (razi.pro storage, reject third-party URLs), though it does not formalize whether the parameter is required or list any other potential inputs. This is sufficient for an agent to pass the correct argument.

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's function: reading text from character-based documents and returning JSON { text, metadata }. It also explicitly contrasts this with extract_text_ocr, making the tool's niche unmistakable.

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 and when-not-to-use guidance: use for text-based files like .txt, not for scanned/images or PDFs, which should go to extract_text_ocr. It also gives constraints on file URLs and rate limits, leaving no ambiguity about allowed usage.

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 of explaining behavior, and it does so thoroughly. It discloses output multiplicity (one PDF per range vs ZIP for multiple ranges), verbatim copying, storage-URL restrictions, rejection of third-party URLs, REST multipart support, and a rate limit of 20 splits per hour per IP.

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 every sentence earns its place: core purpose, output behavior, distinction from alternatives, transport requirements, and rate limit. It is front-loaded with the main action and avoids redundant restatements of the tool name.

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 no output schema and no annotations, the description is remarkably complete. It explains return behavior (PDF vs ZIP), input requirements via fileUrl, REST alternative, when to use compress_pdf or pdf_to_images, and the rate limit, leaving the agent enough context 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 description coverage is 100%, so the schema already fully documents the `ranges` parameter syntax, clamping, and dropped pages. The description adds context about one output file per range and ZIP behavior, but that is more about output semantics than parameter semantics, so the 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 opens with a specific verb and resource: 'Extract page ranges from one PDF into new PDFs.' It clearly distinguishes the tool from siblings like compress_pdf by stating pages are copied verbatim and 'does not reduce file size (use compress_pdf)', making the purpose unambiguous.

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 explicitly tells the agent when not to use this tool and which alternative to pick: 'this does not reduce file size (use compress_pdf) or rasterise pages (use pdf_to_images)'. It also specifies the input requirement over MCP ('pass fileUrl') versus REST, so the agent knows exactly how to invoke it in the correct context.

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