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

Annotations declare destructiveHint=true, and description adds that it removes comments and finalizes the document. This aligns well, though it could explicitly mention irreversibility. Still, combined with annotations, the behavior is clear.

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 efficient sentences, each serving a distinct purpose: first explaining the operation, second providing usage guidance. No extraneous 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?

For a simple tool with two parameters and an output schema, the description fully covers the operation, its outcome, and usage context. No information 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?

Input schema provides 100% description coverage for both parameters. Description does not add any additional semantic value beyond what is already in 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?

Description clearly states it accepts all tracked changes and removes comments to produce a finalized document. It uses specific verbs and distinguishes itself from process_document_batch by emphasizing single operation vs. selective processing.

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?

Explicit when-to-use (when review is entirely complete) and when-not-to-use (for selective changes), with direct mention of alternative sibling tool process_document_batch.

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 full burden. It discloses that drafts are created in the native draft box (not sent), supports Markdown body, and accepts attachments (PDF/DOCX) via absolute paths. It does not mention permissions, limits, or what happens on failure. This is adequate but could add more safety context. Score 4.

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 paragraph that first states the main function, then explains two modes, then attachments, then body format. Every sentence is informative; no redundant or vague statements. It is appropriately sized for the complexity. Score 5.

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 has 5 parameters and no output schema. The description explains input semantics well but omits what the tool returns (e.g., draft ID or success status). Given the complexity and that sibling tools like search_and_fetch_emails have IDs, the return value is important for chaining. Completeness is slightly lacking, so 3.

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%, baseline 3. The description adds significant value by explaining the relationship between parameters and the two modes (NEW vs REPLY). It clarifies that reply_to_email_id is required for REPLY, and subject/to_recipients are required for NEW. This goes beyond individual parameter descriptions and provides usage logic. Score 5.

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 it creates an email draft in the user's native draft box (Outlook/Gmail). It distinguishes between starting a NEW email and REPLYING to a thread, and references the sibling tool search_and_fetch_emails for the reply ID. This specificity and differentiation merits a 5.

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

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

The description explicitly provides two modes (REPLY vs NEW) with conditions for each: for REPLY, provide reply_to_email_id; for NEW, provide subject and to_recipients. It also instructs on attachment paths. However, it does not state when NOT to use this tool nor list alternatives, missing full comparatives. Still, the guidance is clear and useful, so 4.

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 indicate readOnlyHint=true, and the description adds operational details about compare_clean parameter behavior and output format. No contradictions.

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 sentences front-load purpose and usage, with no redundant information. 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 file comparison tool with output schema and annotations, the description adequately covers behavior and parameters. It does not address error conditions but that is acceptable given the output schema fills return details.

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 descriptions already cover all parameters (100% coverage); the description adds nuanced context about the compare_clean flag's effect on tracked changes, enhancing understanding.

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 'Compares two DOCX files and generates a text-based Unified Diff', specifying a specific verb and resource. It distinguishes from siblings as no other tool performs comparison.

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 includes 'Use this to see exactly what changed between two versions of a document', providing explicit guidance. However, it does not mention situations to avoid or alternative tools.

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?

Description adds the key side effect of opening a browser window for authentication, which is not covered by the openWorldHint annotation. It does not detail if user interaction is required or if it's blocking.

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 that are front-loaded and concise. 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?

The description covers purpose and behavior adequately. With 0 parameters and an output schema available, it is fairly complete, though it could mention idempotency or prerequisites like being logged out first.

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?

Input schema has 0 parameters, so no parameter documentation is needed. Description does not need to add param semantics.

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 logs the user into Adeu Cloud backend via secure browser authentication, with specific verb 'logs' and resource 'Adeu Cloud backend'. It distinguishes from the sibling 'logout_of_adeu_cloud'.

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 authentication but does not provide explicit guidance on when to use or when not to (e.g., if already logged in). No alternatives 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?

Description discloses that the tool clears the local API key from the OS Keychain, which is a destructive action beyond the openWorldHint annotation. No contradiction.

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 sentence, concise, front-loaded with the core action. No 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?

Given the tool's simplicity (no params, output schema exists), the description fully covers purpose and side effects. No 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?

Tool has no parameters and schema coverage is 100%, so description does not need to add parameter details. It is adequate.

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 the action (logs out) and the resource (Adeu Cloud backend), and implicitly differentiates from the sibling tool login_to_adeu_cloud.

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 does not explicitly state when to use or when not to use, but the context of logout vs login makes usage obvious. No exclusions or alternatives 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?

The annotation openWorldHint: true already indicates external side effects. The description adds value by specifying 'native desktop application', clarifying the nature of the side effect. Additional details (e.g., dependency on file associations) would improve transparency.

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?

A single, front-loaded sentence with no redundancy. Every word serves a purpose.

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 parameter and an output schema (presumably handling success/error), the description is adequate. It could mention the return type or edge cases, but overall completeness is high.

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%, and the description does not add meaning beyond the schema's definition of 'file_path' as 'Absolute path to the file to open.' Baseline 3 applies.

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

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

The description clearly specifies the action ('opens') and the resource ('local file'), and includes an example ('Microsoft Word for DOCX files') that distinguishes it from sibling tools like read_docx or diff_docx_files.

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 (e.g., read_docx for content extraction). The description merely states what it does without context for selection.

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 provide destructiveHint: true. The description adds valuable context: all changes evaluate against original state, accept/reject actions cascade, and author_name is required for tracked changes. It also warns against manually writing CriticMarkup tags. This goes beyond the annotation but could mention more about output behavior.

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 well-structured with sections and front-loaded with purpose and critical notes. While it is lengthy, the complexity of the tool justifies the length. Each part earns its place, though minor redundancy exists (e.g., repeated 'CRITICAL').

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 (multiple change types with detailed behaviors), the description covers nearly all necessary context. The schema provides 100% parameter coverage, annotations indicate destructiveness, and an output schema exists (so return values are covered). The description is complete for effective use.

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%, but the description adds significant meaning: for 'modify', it emphasizes including surrounding context for unique matching and explains Markdown support; for 'accept'/'reject', it notes cascading behavior; for row operations, it provides details on anchor text. This greatly enhances understanding 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 tool applies a batch of structural edits, text modifications, and review actions to DOCX files, and identifies it as the primary editing tool. It distinguishes from sibling tools like accept_all_changes and sanitize_docx by specifying batch 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 explicitly states it is the primary tool for editing DOCX files and provides a critical guideline about not sending sequential edits that depend on each other within the same batch. It does not explicitly list when not to use the tool, but the context from sibling tools (e.g., read_docx for reading) implies appropriate use.

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 adds significant behavioral context beyond the readOnlyHint annotation, including pagination behavior, CriticMarkup handling, page boundary differences between clean_view settings, and mode-specific behaviors. No contradictions with annotations.

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

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

The description is structured with clear sections and front-loaded purpose. It is moderately detailed but every sentence adds value. Could be slightly more concise, but overall well-organized.

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 4 parameters and no output schema, the description explains input options and return format (text with CriticMarkup, outline structure, pagination). It covers the essential aspects for a read tool, though lacks error scenarios.

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 baseline is 3. The description adds meaningful explanations: clean_view explains CriticMarkup vs accepted text, mode explains outline vs full, page explains 1-indexed pagination. This adds value beyond the 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 'Reads a DOCX file and extracts its text content', which is a specific verb+resource. It distinguishes between modes and clean_view options. However, it does not explicitly differentiate from sibling tools like diff_docx_files or sanitize_docx, though the purpose is clear.

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

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

The description provides explicit guidance on when to use each mode (outline for large documents first, clean_view for final text, page for pagination). It does not state when not to use this tool, but the context is clear enough for an agent to infer appropriate usage.

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

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

Annotations declare destructiveHint: true, and the description reinforces the destructive nature by detailing what is stripped and that an audit report is produced. It adds significant context beyond annotations, such as the three modes and the specific metadata removed. No contradiction with annotations.

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

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

The description is two sentences plus a short list of modes. It front-loads the purpose, then usage, then modes. Every sentence provides value with no redundancy. 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 has an output schema, the description does not need to detail return values. It covers the main behavioral aspects (three modes, audit report, metadata stripping). It could mention handling of invalid files or overwrite behavior, but the input schema provides output_path defaults. Still, it is very complete for a complex tool.

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

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

Schema description coverage is 100%, but the description enriches parameter meaning by mapping parameters to the three modes (full scrub, keep-markup, baseline). For example, keep_markup corresponds to the keep-markup mode, baseline_path to the baseline mode, and accept_all is used in full scrub. The author parameter is also contextualized.

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 sanitizes a DOCX file by stripping dangerous metadata and producing an audit report. It lists specific items removed (rsids, author names, etc.) and describes three modes, distinguishing it from siblings like accept_all_changes or diff_docx_files.

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?

Explicit usage context is provided: 'Use this before sending documents to external parties.' The three modes give guidance on when to use each (e.g., keep-markup for redline to counterparty). However, it does not directly exclude alternatives or say when not to use; the sibling list provides alternatives but no explicit comparison.

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 annotation readOnlyHint=true contradicts the description's claim that the tool downloads attachments to local disk, which is a write operation. This inconsistency misleads the agent about the tool's 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?

The description is clear and front-loaded with core purpose. While slightly verbose (10 sentences), each sentence adds value and there is minimal 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 tool with 11 parameters and no output schema, the description covers essential context: default folder behavior, fetch mode, attachment handling, and working directory. It lacks details on return format but is otherwise complete.

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

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

Schema coverage is 100%, baseline 3. The description adds value by providing usage examples (e.g., 'is_unread=True', 'days_ago=7'), explaining the behavior of email_id (accepts short IDs or Adeu IDs), and recommending working_directory for attachment storage.

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 searches the user's live email inbox and fetches full email with attachments when an email_id is provided. It differentiates the two modes and is distinct from sibling tools like create_email_draft.

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 explains when to use the fetch mode (by providing email_id) and gives specific filter examples. It also cautions about using 'folder=all' only when explicitly requested. However, it does not explicitly contrast with sibling tools or exclude any use cases.

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

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

The description discloses key behavioral traits beyond annotations: it returns a task_id immediately, polls for up to 50 seconds during status checks, and advises to continue if timed out. This aligns with the openWorldHint annotation indicating state mutation. No contradiction with annotations.

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

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

The description is concise at four sentences, with the purpose front-loaded. It effectively communicates the essential information without unnecessary detail, though it could be slightly more terse.

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 asynchronous two-phase nature of the tool and the absence of an output schema, the description adequately covers the flow: starting, getting a task_id, checking status with polling, and timeout behavior. It could mention potential errors or result format, but it is generally complete.

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

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

Although the input schema covers both parameters (100% coverage), the description adds significant value by explaining the usage pattern: how to start a validation with file_paths and how to check status with task_id. This clarifies the conditional logic that the schema alone does not convey.

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

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

The description clearly states the tool's function: validating documents for inconsistencies, contradictions, and risk assessments. It differentiates between starting a new validation and checking status, using specific verbs and resource terms. This distinguishes it from sibling tools like diff_docx_files or sanitize_docx.

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

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

The description provides explicit instructions on when to use the tool for starting vs. checking a validation, including the required parameters for each case. However, it does not mention when not to use it or suggest alternative sibling tools for similar tasks.

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