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

With no annotations, the description carries the transparency burden. It explains the two mechanisms for adding fields (placeholder tags and explicit positions), which is useful, but it does not disclose mutation semantics—such as whether existing fields are replaced, versioning behavior, or required permissions. The description adds partial context beyond the schema but leaves key behavioral details unspecified.

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, front-loaded sentence that efficiently captures the core action and the two modes of operation. There is no redundant wording, and every clause contributes meaningful 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 the tool's complexity (nested objects for fields and overrides, no output schema, no annotations), the description covers the main use cases but does not mention result behavior or side effects. The parameter-rich schema compensates for many details, making the description adequately complete for a focused tool description, though it could be slightly more explicit about the outcome.

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 100%, so the baseline is 3. The description adds value by clarifying that fieldOverrides refine placeholder tags, which is not obvious from the schema's generic 'Per-field overrides keyed by field name' description. It also aligns the 'fields' parameter with 'explicitly positioned fields', enhancing understanding beyond raw schema 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 states the tool adds interactive form fields to a stored PDF, using a specific verb ('Add') and resource ('stored PDF'). It also distinguishes two modes: from placeholder tags refined via fieldOverrides and explicitly positioned fields, which separates it from sibling tools like extract_form_data or flatten_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 conveys clear context for when to use this tool—when adding form fields to a PDF—by outlining the two supported input methods. It does not explicitly name alternatives or state when not to use it, but the purpose is unambiguous given the sibling tool names.

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, description bears full burden. It states the tool reduces size without visual changes, but does not disclose permissions needed, whether original document is affected, or any rate limits or side effects.

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?

Single, well-structured sentence that front-loads the core purpose with zero wasted words.

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 compression tool with one required parameter and good schema, description is adequate. Lacks details on return value or original document handling, but acceptable given tool simplicity.

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 100%, providing full parameter documentation. Description adds no additional parameter meaning beyond what the schema already provides.

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?

Description uses specific verb 'compress/optimise' and resource 'PDF', clearly stating the action and outcome (reduce file size without changing visual content). This distinguishes it from siblings like flatten_pdf or protect_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?

Description implies usage when file size reduction is needed, but does not provide explicit when-to-use, when-not-to-use, or mention of alternatives like flatten_pdf for structural changes.

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?

Annotations are absent, so the description must carry the behavioral burden. It discloses a key non-obvious behavior: creating the envelope does not send it; it returns an envelope in 'created' status, and sending is a separate step (send_envelope). This is meaningful beyond the tool name. It does not discuss failure modes or side effects, but the main lifecycle behavior is covered.

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?

Two sentences contain all essential information: what the tool does, what it returns, and what to do next. No filler, no repetition of schema details, and the most important scoping constraint is front-loaded.

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 creation tool with nested parameters and no output schema, the description covers the key context: input source documents must already exist, the result is 'created' not sent, and the follow-up tool is send_envelope. A small gap is that it never mentions how to identify the returned envelope when calling send_envelope, but the workflow is otherwise clear.

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 input schema already documents all four parameters and their nested structure. The description adds only context that 'existing PDFGate documents' are required, which mirrors the schema's sourceDocumentId description. Baseline 3 is appropriate — no additional parameter nuance is provided.

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 action ('Create a signing envelope'), a specific resource ('from one or more existing PDFGate documents'), and the resulting state ('envelope in created status'). This clearly distinguishes it from siblings like send_envelope, get_envelope, and void_envelope.

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 tells the agent when to use the tool: when a signing envelope should be built from already-existing PDFGate documents. It also states the follow-up action — call send_envelope to dispatch signing emails — which provides clear workflow guidance. It stops short of explicitly saying 'use upload_file first' or listing when not to use it, so it is slightly below a perfect score.

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 behavioral disclosure burden. It meaningfully reveals that the response contains a signing secret and instructs the agent to store it securely for signature verification—important stateful behavior beyond the input schema. It does not mention other side effects, but the most critical one is covered.

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?

Two sentences, no fluff, and the primary action is front-loaded. The security note is valuable and earns its place. Perfectly sized for the tool's complexity.

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 creation tool with no output schema, the description covers the purpose and the most critical response behavior (the signing secret). It doesn't describe the full response shape or mention the webhook ID, which would be useful for later get/delete operations, but the core invocation context is adequate.

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 baseline is 3. The description does not add any detail about the parameters themselves (url, eventTypes, description); all parameter meaning derives from the schema. No extra guidance is needed, but no value is added either.

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 a specific verb ('Create') and resource ('PDFGate webhook subscription'), making it easy to distinguish from siblings like get_webhook and delete_webhook. The action and object are unambiguous and correctly scoped.

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?

No guidance is provided on when to use this tool versus alternatives such as get_webhook or delete_webhook, nor any mention of prerequisites or setup steps. The usage context is only implied by the verb 'create'.

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 must carry the full burden. It merely says 'Delete' without disclosing that deletion is permanent, irreversible, or requires specific permissions. For a destructive action, this is a significant gap.

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, efficient sentence with no unnecessary words. It is front-loaded and immediately conveys the action.

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 tool is simple and has no output schema, but the description is minimal. It lacks information about return values or side effects. While the core purpose is clear, the description does not fully prepare an agent for the tool's complete behavior.

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 has 100% coverage with a single parameter. The description repeats the schema's description ('The document ID to delete') without adding extra meaning, such as format examples or constraints. 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 clearly states 'Delete a PDFGate document.' The verb 'delete' and the resource 'PDFGate document' are specific and distinct from sibling tools like upload_pdf, get_document, etc., which do not involve deletion.

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?

No explicit guidance is given on when to use this tool versus alternatives. Although the tool is simple, there is no mention of prerequisites (e.g., check if document exists) or consequences (e.g., irreversibility). A score of 3 reflects the lack of such guidance.

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 behavioral disclosure. It reveals permanent deletion, that signed documents and audit logs are removed, that recipient data is anonymized and access is lost, that source documents are untouched, and that the action cannot be undone. This is thorough for a destructive operation.

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 compact and information-dense: the primary action and primary consequence come first, followed by eligibility constraints, then the irreversibility warning. Every sentence carries meaningful information with no 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?

For a single-parameter destructive tool with no output schema, the description covers the behavior, side effects, restrictions, and prerequisite action. Nothing essential for an agent to invoke the tool 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 100%, with the only parameter 'envelopeId' described. The description adds no further formatting or semantic detail about the parameter itself, but since the schema already documents it, the baseline score of 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 states a specific verb ('delete') and resource ('envelope'), and immediately clarifies scope: it deletes the envelope plus its produced files (signed documents and audit logs). This differentiates it from siblings like delete_document and void_envelope, making the tool's purpose 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?

It explicitly lists which statuses are eligible ('draft', 'completed', 'expired', 'voided') and tells the agent to 'void an active envelope first', directly pointing to the correct alternative workflow (void_envelope) for active envelopes. This is clear when-to-use and when-not-to-use guidance.

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?

Discloses main consequence (stops event delivery), but no mention of authorization, idempotency, or reversibility. Adequate for a simple delete operation with no 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?

Two concise sentences, front-loaded with action, no wasted words.

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 tool with one param and no output schema, description sufficiently covers purpose and immediate effect.

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 parameter fully (100% coverage). Description adds no extra meaning beyond 'The webhook ID to delete'.

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?

Description clearly states action ('Delete a PDFGate webhook subscription') and consequence ('Future events will no longer be delivered'). Distinguishes from sibling 'create_webhook'.

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?

Implied usage for deleting a webhook, but no explicit guidance on when to use vs. alternatives, prerequisites, or exclusions.

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 must carry the burden. It discloses the return format ('embedded resource') which adds value, but it does not explicitly state that the operation is read-only, or mention authentication, error behavior, or any side effects. The word 'Download' implies a safe read, but this is not made explicit.

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?

Two short sentences with the action and resource front-loaded. The second sentence provides a helpful alternative. No unnecessary words or repetition.

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 tool is simple with one parameter and no output schema. The description covers what the tool does, the return type, and differentiates from get_document. It lacks edge-case details like invalid document IDs or permissions, but these are not critical for a straightforward download operation.

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 100% with a description for the only parameter (documentId = 'The document ID'). The tool description adds no additional parameter semantics beyond what the schema already provides, so 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?

Uses specific verb 'Download' and resource 'raw PDF bytes of a stored document', which clearly differentiates from sibling tool get_document that provides a shareable link. The purpose is unambiguous and distinct.

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 states when to use this tool versus alternative: 'For a shareable link instead, use get_document.' This provides clear guidance on tool selection and contexts where this tool is preferred.

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 burden of behavioral disclosure. It mentions the return value (a JSON object mapping fields to values), which adds some transparency, but it doesn't explicitly state whether the operation is read-only, if any side effects occur, or how errors are handled. The verb 'extract' implies a non-destructive read, but this is left implicit.

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 two sentences long, front-loaded with the action, and contains zero fluff. Every word earns its place, making it highly concise and well-structured.

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 low complexity (1 parameter, no output schema), the description adequately covers the primary behavior and return format. It doesn't specify error conditions or edge cases (e.g., non-fillable PDFs), but for a simple extraction tool this is a minor gap. The absence of a return schema is compensated by the explicit description of the JSON output.

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% (single parameter documentId clearly described as 'The document ID of the fillable PDF'). The description adds no additional parameter semantics beyond what the schema already provides, so a baseline score of 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 clearly states the verb 'Extract' and the resource 'form field values from a fillable PDF', distinguishing it from sibling tools like flatten_pdf (which flattens fields) and add_form_fields (which adds fields). It unambiguously identifies the tool's core function.

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 offers no guidance on when to use this tool versus alternatives such as get_document or flatten_pdf. It doesn't mention prerequisites (e.g., the PDF must be fillable) or scenarios where this tool is preferred. No explicit when/when-not instructions are provided.

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 exist, so the description carries the full burden. It discloses that the tool creates a new document and does not overwrite the original, which is a key behavioral trait. However, it does not mention permissions, side effects (e.g., form data removal), or rate limits.

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 extremely concise with two sentences that front-load the primary action and result. No redundant or unnecessary words.

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 straightforward tool with no output schema, the description covers the essential behavior. It could mention what is returned (e.g., the new document ID) but is still fairly complete given the tool's simplicity.

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 explains all parameters. The description adds no extra semantic value beyond what is in the schema, resulting in a baseline score of 3.

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 flattens an interactive PDF into a static, non-editable PDF. It uses specific verbs ('flatten' and 'creates') and distinguishes the action from sibling tools like compress_pdf or protect_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 does not explicitly guide when to use this tool vs alternatives. However, the purpose is clear enough that an agent could infer usage context. No exclusions or when-not-to-use guidance is provided.

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 full burden. It only states the action without disclosing behavior like error handling, timeouts, authentication needs, or side effects. For a tool with 18 parameters and no output schema, this is insufficient.

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 extremely concise (one sentence, 13 words) with no wasted words. It front-loads the core purpose and key constraint, making it easy for an agent to quickly grasp the tool's function.

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 (18 parameters, no output schema, many siblings), the description is too brief. It doesn't explain the output format, how to combine parameters, or provide an overview. The agent would lack information to use the tool effectively beyond basic usage.

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 high (94%), so the schema already documents most parameters. The description adds value by highlighting the mutual exclusivity of url and html, which is not enforced in the schema. However, it does not elaborate on other parameters or their interactions.

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 generates a PDF from a URL or raw HTML, specifying the two primary inputs and the mutual exclusivity constraint. This distinguishes it from sibling tools like flatten_pdf or protect_pdf, which perform different PDF operations.

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 basic guidance on parameter selection ('Provide either url or html, not both') but lacks information on when to use this tool versus alternatives like upload_pdf or get_document. No explicit when-not or context for choosing among siblings.

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 must disclose behavioral traits. It states 'retrieve metadata' implying read-only, but omits the key behavior of generating a pre-signed download URL via the preSignedUrlExpiresIn parameter, which could have destructive implications if misinterpreted.

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 sentence of 11 words, concise and front-loaded. However, it omits important information, but that is a completeness issue, not a conciseness flaw.

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 two parameters, no output schema, and no annotations, the description should cover the tool's functionality fully. It fails to mention the pre-signed URL generation and does not describe the returned metadata structure, leaving gaps.

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 description coverage is 100%, the description adds no value beyond the schema. It fails to mention the preSignedUrlExpiresIn parameter, which is a significant optional feature, leaving the agent unaware of its purpose.

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 verb 'Retrieve' and the resource 'metadata for a stored PDFGate document by its ID'. It effectively distinguishes the tool from siblings like delete_document or upload_pdf by specifying metadata retrieval.

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 no guidance on when to use this tool versus alternatives such as get_envelope or other tools. No context on prerequisites, exclusions, or preferred scenarios is given.

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 for behavioral transparency. It correctly identifies the operation as a read ('retrieve') and details the output scope (status, progress, per-recipient status). It does not mention auth needs or rate limits, but for a simple retrieval, this is sufficient.

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, well-structured sentence that front-loads the verb and resource. Every word adds value with no 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?

For a simple retrieval tool with one parameter and no output schema, the description fully explains what is returned (status, document progress, per-recipient signing status). No further information is needed.

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 100% with a clear description of 'envelopeId'. The tool description adds no additional meaning beyond what the schema already provides. According to the rubric, baseline is 3 when schema is complete.

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 verb 'Retrieve' and the resource 'envelope', specifying the included fields (status, document progress, per-recipient signing status). It effectively distinguishes itself from siblings like get_document (which retrieves file content) and create_envelope/send_envelope (which are mutations).

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 usage when needing envelope state but provides no explicit guidance on when to use this tool versus alternatives (e.g., get_document for document files). The sibling set provides context, but the description itself lacks proactive direction.

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 must disclose behavioral traits. It states the tool retrieves a subscription, implying a read operation, and likely returns the webhook details; however, it does not mention whether the webhook must belong to the authenticated user, whether it returns a 404 for missing IDs, or any rate limits. The description adds minimal behavioral context beyond the verb 'retrieve'.

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 sentence, under 15 words, and immediately states what the tool does and its key parameter. There is no filler or redundant detail.

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 low complexity (one required parameter, no output schema, no nested objects), the description is sufficient to understand the basic operation. However, the lack of usage guidance and behavioral transparency (e.g., error behavior) prevents a higher score, especially since no annotations offload that burden.

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 single parameter 'webhookId' has a schema description ('The webhook ID') and is required. Schema coverage is 100%, and the description's phrase 'by its ID' corroborates the parameter's role, adding no extra meaning but not detracting. Baseline is 3 for high coverage, and the alignment with the purpose earns a 4 because it reinforces the parameter's necessity.

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 the tool retrieves a webhook subscription by ID, which is clear and differentiates from siblings like create_webhook and delete_webhook. However, it does not specify whether the returned data includes the webhook's URL or events, but the core purpose is 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?

The description gives a straightforward when-to-use scenario (retrieve a webhook by ID) but provides no guidance on when not to use it or when to prefer alternatives, such as list operations. Given the sibling set includes other webhook operations, this lack of context is a gap.

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?

The description discloses that the tool is non-destructive (produces a new document, original unchanged), which is valuable behavioral context beyond the schema. With no annotations, this clarity is helpful, though it could mention more about permission requirements.

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?

Two sentences, front-loaded with the core action, no wasted words. Every sentence adds value.

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 10 parameters, no output schema, and no annotations, the description is concise but lacks detail on return values (e.g., new document ID) and edge cases. It covers the essential function but leaves gaps.

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 parameters are well-documented. The description only adds high-level context about 'optional permission restrictions', not significantly beyond the schema, so 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 clearly states the tool encrypts a PDF with a password and optional permission restrictions, and explicitly notes it produces a new document. This distinguishes it from siblings like compress_pdf or watermark_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 implies usage for protecting PDFs but does not provide explicit guidance on when to use this tool versus alternatives like watermark_pdf or flatten_pdf. No exclusions or prerequisites are mentioned.

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 behavioral burden. It usefully discloses that signing emails are dispatched with OTP-protected links and that links expire with the envelope. It does not mention state changes (e.g., envelope becomes sent and immutable) or whether resending is allowed.

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?

Two sentences, no filler, with the main action front-loaded and a concise behavioral detail following. Every sentence earns its 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?

For a one-parameter tool, the description covers the core action and a key behavioral consequence. However, with no annotations and no output schema, it leaves gaps around result handling, error behavior, and what happens if the envelope was already sent.

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 baseline applies. The description adds a little context by implying envelopeId must refer to a created envelope, but it does not otherwise enrich the parameter meaning beyond 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 uses a specific verb-resource pair: 'Send a created envelope to its recipients.' This clearly distinguishes it from sibling tools like create_envelope, void_envelope, and get_envelope.

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 scopes use to 'created' envelopes and states that recipients will receive signing emails, giving clear context for when to call it. However, it does not name alternative tools or explicitly state when not 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?

With no annotations provided, the description carries the full burden. It discloses the core behavior (upload and storage for later reference) but omits details like persistence duration, size limits, or whether re-uploading overwrites. It does not contradict itself but is minimal.

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?

Two sentences, both purposeful. First states what it does and why; second clarifies the primary input choice. No wasted words, front-loaded with key 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?

The description covers the essential upload action and purpose but lacks detail on the return value (e.g., document ID for referencing) and does not mention optional parameters (metadata, preSignedUrlExpiresIn). Given the tool's simplicity and absence of output schema, it is adequate but not thorough.

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 covers all parameters with descriptions, but the description adds critical semantics: it clarifies that either filePath or url must be provided (mutual exclusivity) and that filePath refers to a local path. This goes beyond the schema, which lists them as separate optional properties.

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 specifies the action (upload a PDF), the target platform (PDFGate), and the purpose (to be referenced by other operations). It clearly distinguishes from sibling tools by focusing on the upload step, not PDF processing or retrieval.

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 that this is a prerequisite for other operations ("so it can be referenced"), implying it should be used before consumption. It does not explicitly mention alternatives or when not to use it, but the purpose is unambiguous.

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. It discloses key behavioral traits: notification to unsigned recipients, invalidation of signing links, non-effect on fully signed documents, visibility of the reason to recipients, and irreversibility. It does not mention auth requirements or side effects on other systems, but covers the core mutation semantics well.

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?

Three concise sentences deliver high-value information with no filler. The action and status constraint are front-loaded, followed by recipient impact, the reason visibility, and irreversibility. Every sentence earns its 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?

For a two-parameter, irreversible action tool, the description covers the operation's scope, side effects, and parameter semantics sufficiently. Since no output schema exists, the description does not need to detail return values. The status restriction answers what conditions are valid, and irreversibility warns against misuse.

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 100% for both parameters, so the baseline is 3. The description adds value by explaining that 'reason' is visible to recipients and included in the cancellation email, which goes beyond the schema's bare description. It also makes clear that envelopeId is the target of the void action.

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 specific action (void/cancel), a specific resource (envelope), and the applicable statuses ('created' or 'in_progress'). It also distinguishes behavior from other envelope operations by noting the effect on unsigned recipients and that fully signed documents are unaffected.

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 clearly says the tool applies to envelopes in 'created' or 'in_progress' status and what happens to recipients, which guides when to use it. It does not explicitly name alternative tools or situations where another tool would be preferred, but the status limitation and irreversible nature give clear contextual guidance.

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 must fully disclose behavioral traits. It states the tool applies a watermark but omits critical details such as whether the original PDF is modified or a new copy is created, required permissions, or limitations on file size or supported formats. The lack of transparency increases risk for the agent.

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 two sentences, very concise, and front-loaded with the primary action. It avoids unnecessary words and is easy to parse. It could be slightly more structured (e.g., bullet points for conditional parameters) but remains highly efficient.

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 (16 parameters, no output schema, no annotations), the description is too minimal. It fails to explain the output or side effects, lacks context for deciding between text and image watermarks, and does not address any potential pitfalls. A more complete description is warranted for such a parameter-rich 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?

The input schema has 100% description coverage, so each parameter already includes semantic meaning. The description adds a small conditional usage note ('For type='text' provide 'text'; for type='image' provide 'watermarkImagePath''), which aligns with the schema. This is adequate but not significantly additive beyond 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 clearly states the action ('Apply a text or image watermark') and the target resource ('a PDF'). It specifies both the text and image variants, effectively distinguishing the tool's purpose from sibling tools that perform different PDF operations.

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 hints at conditional parameter usage based on type but does not provide guidance on when to prefer watermark_pdf over siblings like flatten_pdf or compress_pdf. There is no explicit 'when to use' or 'when not to use' guidance, leaving the agent to infer context from the tool name alone.

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