Reclypse Utility Node

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

With no annotations, the description does real work by disclosing boundary preference and, critically, that concatenated chunks reproduce the input exactly and that limits are measured in code points rather than model tokens. However, the final two sentences about retail prices, payment streams, and prepaid credits are entirely unrelated to this tool and degrade confidence in the rest of the 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 first three sentences are tight and front-loaded, but the last two sentences are off-topic filler that a reader cannot connect to chunking. That is roughly 40% of the text earning no place.

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 annotations and no output schema, the description must carry the full behavioral burden; it omits the return shape (ordered list of strings is only implied by concatenation), whether overlap exists, and how whitespace-only inputs are handled, while spending two sentences on unrelated content.

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 50%: `document` is described in the schema but `max_chunk_size` is not. The description partially compensates by stating that limits are counted in Unicode code points, which clarifies the unit for `max_chunk_size`, but it never addresses the default of 1000, the 16000 maximum, or behavior when the limit is too small to honor a paragraph boundary.

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 implies splitting via 'Prefer paragraph/sentence boundaries, then split deterministically,' but never states plainly that the tool splits a document into chunks nor how it differs from `clean_and_chunk`, its closest sibling. The title carries most of the actual purpose statement.

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 when-to-use guidance, no mention of prerequisites, and no routing against the sibling tools listed (clean_and_chunk, clean_markdown, sanitize_text, structure_json). The agent must infer that this is the plain text-processing option.

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. 'Atomic transaction' is a genuine behavioral disclosure (all-or-nothing, no partial output), but nothing is said about failure modes, whether the input document is mutated, or what the result looks like. The trailing sentences about prices, payment streams, and prepaid credits are irrelevant boilerplate that actively distracts rather than informs.

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?

Only the first sentence earns its place. The two sentences about retail prices, enabled payment streams, and legacy prepaid credits have no relationship to document cleaning or chunking and should be removed; they read as misfiled boilerplate.

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?

No output schema and no annotations mean the description must cover behavior and results, and it does not. With an undocumented second parameter and no explanation of chunk output shape or ordering, an agent cannot predict what it will receive.

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 50%: the 'document' parameter is well documented in the schema, but 'max_chunk_size' has no description anywhere. The description does not compensate at all — it says nothing about chunk sizing, its default of 1000, or what happens at the 16000 boundary.

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 opening sentence names a specific compound operation: cleaning markdown artifacts plus semantic chunking, performed atomically. 'Compound utility' implicitly signals that it wraps the two sibling tools clean_markdown and chunk_document, but it never names them, so differentiation is left to inference.

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 use this composite tool instead of calling clean_markdown and chunk_document separately, nor any prerequisite or exclusion. 'Compound utility' hints at the combined case but gives the agent nothing actionable to route on.

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 behavioral burden. It usefully discloses that script/style content is ignored, normalization is limited to documented artifacts, and payment is required, but it omits return behavior, error conditions, and whether the operation is purely read-only.

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 purpose is front-loaded and the description is compact across three sentences. The payment sentence is relevant but slightly detached from the core extraction behavior.

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 simple one-parameter tool with no output schema or annotations, the description covers purpose and some limitations. It remains incomplete on parameter expectations and sibling differentiation, which matters given tools like clean_and_chunk and sanitize_text.

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 explain the single `content` parameter. It implies the input is HTML text, but does not clarify the parameter name, format expectations, or what the content should contain.

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 a clear verb and resource: extract text from HTML, ignore script/style content, and normalize formatting artifacts. It does not, however, distinguish this tool from siblings like clean_and_chunk or sanitize_text, leaving overlap ambiguous.

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 indirect usage boundaries by saying it does not promise malformed-Markdown repair or HTML security validation. It does not provide positive when-to-use conditions or name the sibling alternative for those excluded cases.

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; it does disclose determinism and explicitly bounds the safety guarantee, which is genuinely valuable. However, the closing sentence about retail prices and payment streams is irrelevant to a text sanitizer and muddies the behavioral picture rather than clarifying it.

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 first two sentences are dense but front-loaded and on-topic. The third sentence about pricing and payment streams is wholly unrelated to text normalization and does not earn its place, actively distracting the reader.

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?

There is no output schema and no annotations, so the description should explain return shape and behavior for the flagged patterns (e.g., does it rewrite text, list flags, or both), which it does not. The safety disclaimer is a plus, but the missing return semantics and the off-topic payment sentence leave it incomplete.

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% and there is one required parameter (raw_input) whose meaning, constraints, or 65536-character limit the description never mentions. It does not explain whether the input should be raw untrusted text, already-extracted text, or markup.

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 operation ('Unicode/control-noise normalization and selected instruction-pattern flags'), but the phrasing is jargon-heavy and never states plainly what the caller gets back (normalized text, flags, or both). It also does nothing to separate it from close siblings like clean_markdown and clean_and_chunk.

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 a useful negative caveat ('Does not guarantee prompt-injection removal or make untrusted text safe'), but that is a disclaimer, not when-to-use guidance. No condition for choosing this over clean_markdown, clean_and_chunk, or chunk_document is offered.

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 disclose meaningful behavior: it rejects duplicate keys and non-finite values, and default mode preserves non-JSON text without inventing fields. However it says nothing about the return shape or what an error response looks like, and the trailing sentence about 'retail prices' and 'payment streams' is unrelated boilerplate that adds confusion rather than behavioral clarity.

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 first three sentences are dense and front-loaded with the parse scope, mode semantics and rejection rules. The final sentence about retail prices, payment streams and server metadata is irrelevant to a JSON parser and reads as extraneous boilerplate that dilutes an otherwise tight definition.

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 2-parameter tool with no output schema and no annotations, this covers the core parse contract and the non-obvious mode semantics. It leaves the agent without a picture of the return value or error payload, and the payment sentence is unexplained context that does not help an agent decide whether or how to call the tool.

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 define both parameters. It does a good job on schema_target, spelling out the meaning of each of the three enum values, and implicitly defines text as accepting JSON or a fenced block. It omits the 65536-character limit and does not clarify what 'default' returns when text is not JSON.

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 and resource: parse JSON (or a complete JSON code fence), with the title reinforcing 'strict JSON without inference'. It is clearly distinct from the chunking/cleaning siblings, though it never explicitly names or contrasts them, which caps it below a 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 three schema_target modes are described in operational terms ('default preserves non-JSON text without inventing fields; object requires an object; records requires an array of objects'), which effectively tells the agent which mode to pick. There is no explicit when-to-use-this-vs-alternative guidance (e.g. versus sanitize_text) and no stated preconditions beyond payment.

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