Server Quality Checklist

Tool Scores

• turbosign_downloadA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It discloses the key constraint that only completed documents can be downloaded, and that output_path must be an absolute path in an existing directory. While it doesn't detail error handling or side effects like file overwriting, it covers the most critical behavior for a download tool.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences, direct, and without fluff. It front-loads the purpose first, then adds constraints. Every sentence earns its place, making it highly efficient.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple with 2 required parameters and an output schema exists, so return values need not be explained. The description covers the essential purpose and constraints. It could mention behavior on invalid input or file conflicts, but for a basic download tool, it is adequately complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must compensate. It adds meaning to output_path by specifying it must be an absolute path in an existing directory, but does not elaborate on document_id. This partial compensation is insufficient to fully cover both parameters, hence a mid-range score.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's action: 'Download a completed signed document to a local file.' This specific verb+resource combination distinguishes it from sibling tools like turbosign_send or turbosign_status, making its purpose unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides a usage condition ('Only completed documents can be downloaded') and a path prerequisite, but does not explicitly mention alternatives or when to prefer this tool over others. Usage is implied by the tool name and context rather than explicitly contrasted with siblings.

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

• turbosign_statusA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of disclosing behavior. It reports the document and recipient states along with a caveat ('where the API returns them'), which adds transparency. However, it does not explicitly state that this is a read-only operation, nor does it mention potential errors, rate limits, or other behavioral traits.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is only two sentences, front-loaded with the core purpose ('Check where a signature request has got to') and then expands with concrete output details. Every sentence adds value without fluff or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple (one parameter, output schema present), and the description effectively explains the return values and how they can be used (recipient ids for resend). It does not mention error scenarios or edge cases, but given the simplicity and presence of an output schema, the description is sufficiently complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 0% (the schema only shows 'document_id' as a string). The description compensates by explaining that the parameter refers to a signature request/document, but it does not describe how to obtain the ID or any format constraints. For a single, obvious parameter, this is adequate but not fully compensating.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Check') and resource ('a signature request'), and clearly states the tool reports the document's state (pending, completed, voided) and recipient states/ids. This distinguishes it from siblings like turbosign_send, turbosign_void, and turbosign_resend, which perform other actions.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use the tool: to check status and obtain recipient ids. It explicitly ties the output to turbosign_resend ('The recipient ids are what turbosign_resend() needs'), providing a concrete use case. It does not formally list exclusions, but the context is clear.

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

• turbosign_audit_trailA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It details the return format (hash-chained entries), the event types, and the ordering (newest last), which is good. It does not mention side effects, but as a read-only history tool, 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences long, front-loads the core purpose, and avoids unnecessary detail. Every word adds value, making it highly efficient.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple and has an output schema, so return values are already described. The description covers purpose and usage well, but the missing parameter explanations prevent it from being fully complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema description coverage is 0%, and the description provides no explanation of the 'limit' or 'document_id' parameters. It does not even mention them, leaving the agent to infer their meaning solely from the schema names. This is a significant gap.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose with a specific verb and resource: 'Get the tamper-evident history of a document.' It also differentiates from siblings like turbosign_status by focusing on the full audit trail rather than a simple status check.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides a concrete use case (answering 'has Bob opened it yet?'), giving clear context for when to use this tool. It does not explicitly mention alternatives or exclusions, but the use case is specific enough to guide selection.

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

• turbosign_resendA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description bears the full burden of explaining behavior. It usefully discloses that only recipients whose turn it is in the signing order will be emailed, which is a nontrivial constraint. But it does not mention error handling for invalid IDs, whether the operation is idempotent, or any permissions needed. This is a moderate disclosure, not comprehensive.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is extremely concise: two sentences. The first sentence states the core purpose, and the second provides necessary parameter detail and a key behavior. Every word earns its place, with no fluff or repetition of schema fields.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a moderate-complexity tool with two parameters and an output schema, the description is largely complete. It covers the action, the target recipients, the source of the IDs, and the eligibility rule. It omits possible error scenarios and return value details, but the output schema likely covers response structure. The description is sufficient for selecting and invoking the tool confidently.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 0%, so the description must explain parameters. It does explain recipient_ids as a comma-separated list of UUIDs sourced from turbosign_status(). This adds significant meaning. document_id is not explained, but it is a standard identifier and less ambiguous; still, it could have been clarified. Overall strong compensation for the schema gap.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action: 'Resend the signature request email to recipients who have not signed.' This uses a specific verb and resource, and the 'recipients who have not signed' qualifier distinguishes it from the initial send tool (turbosign_send). It is not tautological and provides a precise scope.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use this tool: to nudge signers who haven't signed yet. It also instructs users to retrieve recipient_ids from turbosign_status(), giving a prerequisite. However, it does not explicitly name alternatives like turbosign_send or state when not to use it, though the 'resend' and 'not signed' context makes this fairly clear.

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

• turbosign_reviewA
  4.2/5.0
  Behavior4/5

  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 key behavioral trait: 'WITHOUT emailing anyone' and that it returns a preview URL. It also implies the document is only prepared, not sent, which is critical context. However, it doesn't mention any limitations like URL expiry or document retention, so it's not fully transparent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three concise sentences, front-loaded with the key point. Every sentence earns its place, with no wasted words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite the clear use case and preview URL behavior, the tool has 11 parameters and 0% schema coverage. The description's reliance on 'Same arguments as turbosign_send' doesn't compensate for the lack of parameter documentation, making it incomplete for an agent to invoke correctly without additional context.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema has 0% description coverage, and the description only says 'Same arguments as turbosign_send' without explaining any of the 11 parameters. It fails to add meaning beyond the schema, and the agent must look up another tool to understand required parameters like file_path and recipients.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool prepares a document and returns a preview URL without emailing anyone. It uses a specific verb+resource combination and explicitly differentiates from turbosign_send by highlighting the absence of emailing.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly tells when to use this tool: 'to check where the signature boxes landed before committing to a real send' and 'Worth doing the first time you send a particular kind of document.' This clearly frames it as a pre-send dry run, distinguishing it from the actual send tool.

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

• refresh_toolsA
  4.3/5.0
  Behavior3/5

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

  The description does not have annotations to fall back on, and it provides some behavioral context by positioning the tool as a proper cache-refresh mechanism rather than raw HTTP. However, it does not disclose side effects like whether the refresh is destructive, idempotent, or has network implications. Without annotations, this is a moderate gap.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two concise sentences, front-loaded with the main verb and object, and includes the key usage context and alternative without any fluff. Every word earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's low complexity (zero params, an output schema, and a simple cache-refresh function), the description is fully complete. It covers the purpose, the condition for calling, and the preferred alternative, while the output schema handles return-value documentation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has zero parameters, and the schema coverage is trivially 100%. Per the rubric, 0 parameters receives a baseline of 4, and the description does not need to elaborate on parameter semantics. It adds no parameter details, but none are needed.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool refreshes the client's cached tool list, with a specific trigger scenario ('after a server restart or upgrade'). This specific verb+resource combination distinguishes it from the turbosign_* sibling tools, which are all domain operations.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It explicitly states when to use the tool ('after a server restart or upgrade') and names a clear alternative to avoid ('instead of falling back to raw HTTP requests'). However, it does not explicitly state when not to use it, which would make it a 5.

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

• turbosign_voidA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description fully bears the responsibility. It discloses critical behavioral aspects: the reason is recorded in the audit trail, is required, and the action is irreversible. This provides important context beyond a simple 'cancel' and alerts the agent to potential consequences.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences with no filler. The first sentence states the action and condition; the second conveys key consequences and an alternative. Information is front-loaded and easy to scan.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with only two simple parameters and an output schema, the description covers the purpose, the condition, the required reason, audit trail recording, irreversibility, and a restart path. This is sufficient context for an agent to select and invoke the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema has 0% description coverage, so the description must add meaning. It explicitly states that reason is required and recorded in the audit trail, clarifying why that parameter is needed. document_id is self-explanatory as the target request, so overall the description compensates well for the schema's lack of detail.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb 'Cancel' and a clear resource 'a signature request that has not completed,' which distinguishes it from sibling tools like turbosign_resend or turbosign_send. The condition 'has not completed' further clarifies the scope.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use the tool: only for signature requests that have not completed. It also gives an alternative action ('send the document again') if the user needs to restart. However, it does not explicitly name sibling tools as alternatives or state when not to use it, leaving a minor gap.

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

• turbosign_whoamiA
  4.5/5.0
  Behavior4/5

  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 output contents (masked API key, org id, sender address, resolution source) and the live API check behavior when verify=True. It does not explicitly mention that verify defaults to true, but that is covered in the schema. It is transparent about the main behavioral aspects.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and front-loaded. The first sentence states the core purpose, followed by one concise sentence that lists reported fields and the verify behavior. No fluff or repetition of schema information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple (one optional boolean parameter) and has an output schema, so the description does not need to enumerate return fields. It covers the tool's purpose, output contents, resolution source, and the verify behavior, making it complete for an agent to invoke correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The only parameter, verify, has a schema default but no schema description (0% coverage). The description adds meaning by stating that verify=True triggers a live API credential check, which goes beyond the raw type/default. It does not explicitly describe the false behavior, but the implication is clear.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Show') and resource ('which TurboDocx account this machine sends as'), clearly distinguishing it from sibling tools like send, status, and download. It immediately communicates the identity/diagnostic nature of the tool.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides a concrete use case ('useful when the same server is installed on several machines with different accounts') that helps the agent decide when to invoke it. It does not explicitly state when not to use it or name alternatives, but the context is clear and sufficient for a simple diagnostic tool.

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

• get_instructionsA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It clearly indicates this is a read-only operation via the verb 'return,' and the tool has no parameters or side effects. However, it does not explicitly state 'read-only' or mention any other behavioral traits beyond what the description conveys, but for a simple informational tool 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences long, front-loaded with the purpose, and the second sentence adds actionable usage guidance. No wasted words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple, zero-parameter tool with an output schema, the description fully explains what it returns and when to use it. Given the complexity of the sibling tools, this guidance tool is well-specified.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has 0 parameters, so according to the rubric the baseline is 4. The description correctly omits any parameter details, and the schema coverage is trivially 100%.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: 'Return this server's usage instructions and recommended workflow.' It uses a specific verb ('return') and resource ('usage instructions'), and it distinguishes itself from the sibling tools, which are all turbosign operations or refresh_tools.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly tells when to use it: 'Call this after a context compaction, or whenever it is unclear which tool to reach for.' This gives clear context and implies that if you know which tool to use, you shouldn't call this.

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

• turbosign_configureA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description fully carries the burden. It discloses that credentials are verified against the live API before writing, stored owner-only in a specific path, never echoed back, and that passed values travel through the conversation transcript. No annotation contradiction exists.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is front-loaded with purpose and every sentence earns its place: verification behavior, storage location, parameter semantics, security behavior, and privacy guidance. Despite being long, there is no filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description is complete for a credential-configuration tool: it covers verification, storage, privacy, parameter semantics, and when not to use it. An output schema exists, so return-value details are not required. Nothing important is missing.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must compensate. It explains sender_email as the reply-to address, sender_name's default behavior, and base_url's non-production purpose. However, api_key and especially org_id are only implicitly referenced and not clearly defined, leaving a small but notable gap.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  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: 'Save this machine's TurboDocx credentials after checking they work.' It clearly distinguishes this configuration tool from siblings like turbosign_send or turbosign_setup by focusing on credential storage and verification.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It explicitly says to get values from turbosign_setup(), provides context for when this tool is appropriate (scoped key on a test account), and tells the agent to direct the human to a terminal command instead for long-lived keys or session tokens. This provides both usage context and an explicit alternative.

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

• turbosign_sendA
  4.9/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries the full burden. It warns 'THERE IS NO SANDBOX,' states emails reach real inboxes, and that documents 'cannot be recalled, only voided.' This is exceptional disclosure of production impact, far beyond typical mutation warnings.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is logically organized: a safety warning, a pre-flight checklist, parameter definitions, and return value. Every sentence contributes essential information—no filler or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given 11 parameters and no annotations, the description still covers purpose, safe usage, parameter semantics, and return value. The output schema provides return structure, and the description adds 'Returns the document_id — keep it, every other tool needs it' to support tool chaining. This is fully complete for an agent to use the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, requiring the description to compensate. It thoroughly explains the critical parameters: file_path, recipients, placement (including all four enum values and their behavior), and sequential. However, it leaves 7 optional parameters (e.g., anchor, fields, cc_emails, sender_name) with little or no direct explanation, though these are mostly self-explanatory and have defaults.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description opens with 'Send a document out for signature' — a clear verb+resource pair. It further distinguishes itself from the sibling turbosign_review by explicitly noting review 'takes these exact arguments and emails nobody,' making send's role as the actual email-sending tool unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Provides explicit when-to-use guidance: on new machines or accounts, run turbosign_whoami(verify=True) then turbosign_review() first, and make the first real send to your own address. This names the alternative (turbosign_review) and sets clear preconditions for safe use.

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

• turbosign_setupA
  5/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: it reports which credentials are missing and where present ones came from, provides URLs, and explains that open_browser is best-effort with a rationale (no desktop on server). This is rich, honest behavioral context beyond what the schema alone could convey.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences, each earning its place: the first gives primary purpose, the second details outputs and next steps, the third explains the parameter. No filler, no repetition, and front-loaded with the most important usage cue.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  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 optional param) and presence of an output schema, the description covers all necessary context: what it does, what it reports, how to proceed, and parameter behavior. Nothing essential is missing for an agent to select and invoke it correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema has one optional boolean (open_browser) with zero description coverage. The description fully compensates by explaining exactly what setting it to True does, its best-effort nature, and the reason behind it. This adds significant semantic meaning beyond the raw schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with 'Start here on a machine that has never sent a signature request,' which clearly identifies the tool as a setup/diagnostic utility for first-time configuration. It explicitly states it reports missing credentials and provides URLs for obtaining them, distinguishing it from siblings like turbosign_configure and turbosign_send.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The first sentence provides explicit when-to-use guidance ('never sent a signature request'), and the description instructs to 'call turbosign_configure() with the three values' as the next step, giving a clear sequence. It also explains the optional open_browser behavior, covering edge cases like headless servers.

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