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

Annotations already indicate non-destructive (destructiveHint false). Description adds 'without removing the original', which is consistent but adds little beyond that. No disclosure of other behaviors (e.g., idempotency, folder existence).

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 with no wasted words. Efficient but lacks depth.

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 mutating tool with multiple parameters and no schema descriptions, the description is too brief. Lacks details on error handling, return value (despite output schema existing), and prerequisites like folder existence.

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 0%, so description must compensate. However, description does not explain any parameters. Parameter names (uid, source_folder, etc.) are somewhat self-explanatory but no additional details on format, required constraints, or defaults.

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 (copy) and resource (email message to another folder). Distinguishes from move_email sibling by stating 'without removing the original'.

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 when to use (copying vs. moving) but does not explicitly mention alternatives like move_email or provide context on when not to 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?

Annotations already provide safety profile (non-destructive, non-idempotent). The description adds 'subscribe' behavior, which is helpful but not extensive. 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?

Single sentence is concise and front-loaded. No unnecessary words, but could include a brief note on parameters without harming conciseness.

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 output schema present, the description is fairly complete. Basic parameter info and return value explanation would improve it further.

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 0% with no enum descriptions. The description does not elaborate on the 'folder' or 'account' parameters beyond their names, missing an opportunity to compensate.

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 explicitly states 'Create a new IMAP folder and subscribe to it,' with a clear verb and resource. It distinguishes from sibling tools like delete_folder or rename_folder.

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 when to use (creating IMAP folders), but provides no explicit guidance on when not to use or alternatives. Context from sibling tools is absent.

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 include destructiveHint: true, and the description adds behavioral context: soft-delete by default and the existence of a permanent parameter. This clarifies the degree of destruction beyond the annotation, though it does not mention behavior for already-deleted emails or recovery options.

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. First sentence states the core purpose; second adds a critical behavior detail. Well-front-loaded and 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 5 parameters and low schema coverage, the description only marginally covers the tool's behavior. It explains the delete mechanism but omits details on required parameter uid, optional folders, and output. While output schema exists, the description could still benefit from noting that the tool has a return value.

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?

With schema description coverage at only 20%, the description adds meaning for the permanent parameter by explaining its effect. However, it provides no explanation for uid, folder, account, or trash_folder, leaving several parameters without semantic context. The description partially compensates but not fully.

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 'Delete' and resource 'message', and distinguishes soft-delete (moves to Trash) from permanent deletion. This differentiates it from sibling tools like move_email and delete_folder.

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 deleting emails but does not provide explicit guidance on when to use vs alternatives (e.g., move_email for organizing), nor does it give when-not-to-use scenarios. The context of soft-delete is stated but not compared to permanent deletion.

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 value beyond annotations by specifying that the tool fails if the folder is not empty (per RFC). Annotations already indicate destructiveness and idempotency, but the description provides the emptyness constraint and failure behavior, which is critical for correct invocation.

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 with no wasted words: action, resource, key constraint. Perfectly front-loaded and 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 two parameters (one required) and an output schema, the description covers the core behavior but lacks parameter explanations and any prerequisites. It is adequate for a simple tool but could be more 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?

With 0% schema description coverage, the description should compensate by explaining parameter meaning, but it does not. The terms 'folder' and 'account' are not clarified (e.g., folder path, account identifier), leaving ambiguity for the agent.

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 an empty IMAP folder' with a specific verb and resource, and includes a distinguishing constraint (fails if not empty) that differentiates it from sibling folder operations like create_folder and rename_folder.

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 the folder is empty but does not explicitly state when to use this tool over alternatives, nor does it provide when-not or prerequisite conditions. The constraint 'fails if not empty' gives some guidance, but it lacks direct comparison to 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?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, covering safety and idempotency. The description adds the base64 format detail but omits other behavioral traits like potential large payloads or that missing filenames returns all attachments. 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?

Two sentences with no wasted words. The first sentence fronts the core purpose; the second provides actionable guidance. 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 simplicity, annotations covering safety, and presence of an output schema, the description is largely sufficient. Minor omission: does not mention that omitting filenames downloads all attachments, but this is inferable.

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

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

Schema coverage is 50% (uid and filenames described). The description adds meaning to filenames (saving byte cost) but does not elaborate on folder or account parameters. Overall, it adds some value beyond the schema but leaves gaps.

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 tool returns message attachments in base64 format, with an option to filter by filenames. It specifies the exact resource and action, distinguishing it from sibling tools which focus on reading email content or managing folders/stars.

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 a usage hint ('Filter by filenames to save bytes'), which helps agents know when to leverage filtering. However, it does not explicitly state when to use this tool versus alternatives (e.g., read_email), though as the only attachment downloader, context is clear.

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 destructive and idempotent behavior; the description adds transparency about message modifications (subject prefix, header quoting). No contradictions. Additional behavioral context beyond annotations is present.

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 that covers the essential behavioral characteristics without 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?

Despite having output schema, the description fails to address the complexity of 10 parameters, required fields, or behavior specifics. It is insufficient for an agent to confidently invoke this tool without additional inference.

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 low (20%), and the description does not elaborate on parameter meanings beyond the basic function. Only 'uid' and 'text' are documented in schema; the description adds no parameter guidance.

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 (forward a message) and specifies unique behaviors (subject prefix 'Fwd:' and quoting original headers). This distinguishes it from siblings like reply_email and send_email.

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, no prerequisites, and no exclusions. It only describes the action without contextual usage advice.

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 readOnlyHint, openWorldHint, and idempotentHint, indicating safe non-destructive read behavior. The description adds minimal behavioral context beyond grouping logic, but does not contradict 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 a single concise sentence, directly stating the tool's purpose. While brief, it is front-loaded and lacks unnecessary words. A bit more detail would be justified but current length is 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?

With an output schema present, the description does not need to detail return format. However, it omits any mention of default behavior (e.g., ordering, inclusion of duplicates). Still, minimal completeness is achieved for the given complexity.

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 low (25%). The description does not elaborate on any parameter semantics, leaving the agent without additional meaning beyond the schema's own descriptions (e.g., uid 'Any message UID in the thread').

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 groups messages based on Message-ID/References/In-Reply-To headers, which precisely identifies the action and resource. It effectively distinguishes from siblings like read_email (single message) or search_emails (query-based).

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 read_email or search_emails. It lacks any context about prerequisites, conditions, 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?

Description adds context beyond annotations: explains that no secrets are returned and details mode-dependent behavior (multi-user vs single-tenant). Annotations already indicate read-only and idempotent, so 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?

Two concise sentences. First sentence states purpose and a key trait, second explains behavioral nuance. 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?

Given zero parameters, detailed annotations, and presence of output schema, the description fully covers necessary context including mode-specific behavior and security implication (no secrets).

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?

No parameters, so baseline of 4 applies. Description does not need to add parameter info; schema coverage is 100% with zero params.

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?

Clearly states verb (list), resource (email accounts), and scope (caller can act on). Distinguishes from siblings by focusing on account listing and mentioning no secrets returned.

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?

Provides clear context for when to use (to see which accounts are actionable), but does not explicitly state when not to use or mention alternatives. However, given sibling tools are operation-specific, usage is well implied.

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 already mark it as read-only and idempotent. The description adds behavioral detail about UTF-7 decoding, which is beyond what annotations provide.

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 that conveys the purpose and a key detail. It is front-loaded with 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?

Given the tool's simplicity (one optional parameter, read-only, output schema exists), the description is complete and sufficient for an AI agent to understand 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?

The one optional parameter is already described well in the input schema (100% coverage). The description adds no extra parameter information, so baseline 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 'list', the resource 'IMAP folder (mailbox)', and the scope 'every...the account can see', with an additional detail about UTF-7 decoding. It distinguishes from siblings like list_accounts and list_recent by specifying folders.

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 when to use (to list all folders) but does not provide explicit guidance on when not to use or alternatives. For a simple list tool, this is acceptable but minimal.

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 readOnly, idempotent, openWorld. Description adds 'metadata only, newest first' and pagination behavior, providing context beyond 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 sentences, zero wasted words. Front-loaded with the core action. Efficient and clear.

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 output schema exists (context signal) and annotations cover safety, the description provides essential behavior and pagination. Could mention it lists message headers, but metadata-only is indicated.

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 good descriptions. The description adds no new parameter meaning 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?

Description states 'List the most recent messages in a folder (metadata only, newest first)' – a specific verb+resource with clear scope, distinguishing it from siblings like search_emails or read_email.

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 explains cursor-based pagination with 'Use cursor (=previous next_cursor) to page further back in time.' Lacks when-not-to-use or alternatives, but sufficient for typical 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 already indicate the tool is idempotent and non-destructive, but the description adds no behavioral context beyond stating the action. It does not disclose what happens to existing flags or the response format.

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 one sentence and concise, but it is under-specified. It lacks crucial information, making it minimal rather than efficiently comprehensive.

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 multiple parameters and an output schema, the description is incomplete. It does not explain how parameters affect behavior or what the output contains, leaving significant 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 0%, and the description provides no explanation of the parameters (uid, folder, account). The agent must infer parameter semantics solely from names and types, which is insufficient.

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 'Add the \Seen flag' communicates that the tool marks an email as read, but it is vague and relies on technical jargon. While it distinguishes from mark_unread, it does not clearly state the effect in plain language.

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 like mark_unread or star_email. The agent receives no 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 already indicate idempotent and non-destructive behavior. The description adds only the action of removing the Seen flag, offering minimal additional context beyond the 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 a single sentence, which is concise but lacks structure and essential information. It earns its place but does not provide a complete overview.

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?

Despite having an output schema, the description is too minimal given the tool's three parameters and the presence of siblings. It fails to cover usage context or return value semantics.

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

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

Schema description coverage is 0%, and the tool description does not explain any of the three parameters (uid, folder, account), leaving the agent without necessary context.

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 'Remove the \Seen flag' clearly states the specific action on a specific resource (the Seen flag), distinguishing it from siblings like mark_read.

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 on when to use this tool versus alternatives like mark_read or unstar_email. The description does not mention context or prerequisites.

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 mentions a fallback (COPY+EXPUNGE), which may be destructive, but annotations claim destructiveHint=false. This contradiction is not addressed. Additionally, idempotentHint=true is plausible but not explained. The description does not clarify behavioral traits beyond the basic 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?

One sentence, front-loaded with the core action. Could add a bit more context on fallback behavior without excessive length, but still 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 4 parameters with no schema descriptions, existence of an output schema (undescribed), and potential behavioral contradictions, the description is inadequate. It does not explain return values, prerequisites, or failure states.

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

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

Schema description coverage is 0%, and the description only says 'message between folders', providing no meaning for parameters like uid, account, source_folder, destination_folder. Users must infer from names alone.

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 moves a message between folders, using specific protocol (RFC 6851 MOVE with fallback). This distinguishes it from sibling tools like copy_email (copy) and delete_email (delete).

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?

Usage is implied by the tool name and description (move, not copy or delete), but no explicit guidance is given about when to use this vs alternatives. No when-not-to-use or prerequisites 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?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint. The description adds critical behavioral context: attachments are listed by name+mime by default, and embedding requires include_attachments=true with a size limit caveat. This goes beyond annotations and helps the agent understand context limitations.

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 main purpose, no redundant phrases. 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 the complexity and sibling tools, the description is mostly complete. It could mention that for file downloads, use download_attachments, but the output schema likely documents return values. The caveat about attachment size and context is valuable.

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 50% (2 of 4 parameters have descriptions). The description adds meaning for 'uid' (implying it comes from list_recent/search) and 'include_attachments' (explains behavior and context limit). It does not cover 'folder' or 'account', but their defaults are clear from 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 ('Fetch'), the resource ('message'), and the content retrieved ('full headers + body', 'attachments listed by name+mime'). It distinguishes from sibling tools like list_recent (list messages) or download_attachments (download 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?

The description implies usage for reading a specific email, but does not explicitly state when to use this tool vs alternatives like list_recent or download_attachments. No guidance on when not to use or prerequisites.

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 openWorldHint=true, implying potential unknown side effects, but the description does not elaborate on behavior such as renaming consequences, permissions, or error handling. 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 extremely concise (4 words). While it lacks detail, it is not verbose. It could be improved with a bit more structure, but it is 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 3 parameters (2 required) and an output schema, the description is insufficient. It does not mention return values, errors, or constraints like minLength, which are present in the schema but not explained.

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?

With 0% schema description coverage, the burden falls entirely on the description, which merely states the tool's purpose without explaining the parameters (e.g., what 'folder' and 'new_name' mean, or the optional 'account' parameter). The schema provides names only.

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 and resource: 'Rename an IMAP folder.' It uses a specific verb and resource, and distinguishes from sibling tools like create_folder and delete_folder. However, it could be more precise by including the parameters involved.

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 move_email or create_folder. The description lacks any context about prerequisites or appropriate scenarios.

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 behavioral context beyond annotations: it reveals email threading preservation (Message-ID, Subject prefix). Annotations already mark destructiveHint=true, so 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?

The description is extremely concise: two sentences plus a single note. Every sentence adds value, and the key information 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?

Given 10 parameters and 20% coverage, the description is incomplete. It covers the core purpose and one parameter but lacks details on others. The presence of an output schema partially mitigates this.

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?

With schema description coverage at 20%, the description only adds meaning for reply_all. It does not describe other key parameters like html, text, attachments, etc., leaving agents without needed context.

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 'Reply to a message' and details threading behavior (Message-ID, Subject Re: prefix). This distinguishes it from sibling tools like send_email and forward_email.

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 the reply_all parameter's effect but does not provide when-to-use vs alternatives (e.g., forward, send new), nor when not to use the tool.

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 already indicate write operation (readOnlyHint=false) and idempotence. The description adds minimal behavioral context beyond 'save an unsent draft', lacking details on overwriting, side effects, or authentication 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?

Single sentence, 10 words, front-loaded with key action and target. Efficient but very minimal; could include more detail without losing conciseness.

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 9 optional parameters and an output schema, the description is inadequate. It does not clarify required fields, return structure, or common usage patterns, leaving significant 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 only 11% (one parameter documented). The tool description does not explain any parameters, forcing reliance on the incomplete schema. With 9 parameters, the description should provide summary but does not.

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 (save), the object (unsent draft), and the location (Drafts folder). It distinguishes well from sibling tools like send_email or delete_email.

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 when-to-use or when-not-to-use guidance is provided. While the description implies this is for unsent drafts, it does not mention alternatives or prerequisites, leaving the agent to infer usage context.

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 key behavioral traits beyond annotations: IMAP SEARCH behavior (substring, case-insensitive, no boolean operators) and the fact that the query is wrapped in quotes. Annotations already indicate read-only and idempotent.

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?

Concise two-sentence structure with front-loaded purpose and behavioral note. Could include more detail without being verbose, but 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?

Adequate given existing annotations and output schema; covers search behavior limitations but does not explain the openWorldHint or parameter interactions.

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?

Does not add meaning beyond the input schema; schema coverage is 60% (3 of 5 params have descriptions), but the tool description provides no additional parameter details or clarifications.

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?

Clearly states it performs IMAP SEARCH over one field, specifying the resource (emails). However, it does not explicitly distinguish from siblings, though no other search tools exist.

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?

Provides limitations (substring, case-insensitive, no boolean operators) and suggests chaining calls for richer queries, giving implicit guidance on when to use alternatives.

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?

Beyond annotations (readOnly=false, destructiveHint=true, idempotentHint=true), the description adds valuable behavioral context: supports HTML, attachments, Save-to-Sent, and retry idempotency. It does not cover all side effects (e.g., irreversible send) but adds meaningful info.

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: three sentences that front-load the purpose and then add key details. 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 complexity (12 params, 1 required, many siblings), the description covers main features and retry behavior but lacks usage guidelines and full parameter semantics. Annotations fill some gaps, but completeness is average.

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?

With 58% schema description coverage (7 of 12 params documented), the description adds extra context for html, attachments, save_to_sent, and idempotency_key. However, many parameters (cc, bcc, reply_to, text, account, confirm) are not addressed, so the description only partially compensates for schema gaps.

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 'Send' and resource 'email', and highlights key features (HTML, attachments, Save-to-Sent). This distinguishes it from sibling tools like send_invite, reply_email, or forward_email.

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 vs alternatives such as reply_email, forward_email, or send_invite. The description only hints at retry behavior but not comparative 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 already indicate the tool is write-only, idempotent, and destructive. The description adds the technical detail that it uses RFC 5545 ICS with METHOD:REQUEST, which is useful context but does not disclose behaviors like what happens if the account is not specified or how errors are handled. It does not contradict 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 a single sentence with no unnecessary words. It efficiently communicates the core purpose. However, it is perhaps too concise given the complexity of the tool; a slightly longer description could improve clarity without losing conciseness.

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 high parameter count (16) and the presence of an output schema, the description is too sparse. It does not explain the expected behavior for optional parameters, the format of the ICS file, or how the tool interacts with accounts. More context is needed for an agent to use it correctly without external knowledge.

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 only 6%, meaning only one parameter (start) has a description. The tool description does not explain the meaning or format of any parameter beyond what the names imply. For a tool with 16 parameters, this is insufficient. The description should at least clarify that 'to', 'start', 'end', and 'subject' are required.

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 explicitly states it sends a calendar invite using RFC 5545 ICS with METHOD:REQUEST. This clearly differentiates from sibling tools like send_email, which send standard emails. The verb 'send' and resource 'calendar invite' are specific.

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 provide explicit guidance on when to use this tool versus alternatives. While the intent is implied by naming it 'send_invite' and specifying calendar invite, it does not contrast with send_email or other tools. No when-not-to-use or prerequisite information 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?

Annotations already provide idempotentHint=true and destructiveHint=false, so the agent knows the tool is idempotent and non-destructive. The description adds no additional behavioral context beyond restating the action, so it meets a baseline but provides no extra value.

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, direct sentence that immediately conveys the core action. It is highly concise with no wasted words, making it easy to parse quickly.

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 existence of 21 sibling tools and three parameters with no schema descriptions, this minimal description is insufficient. It lacks information about required parameters (uid), default folder, output, and how to use alongside other tools. Particularly missing is guidance on the effect of repeating the action or handling accounts.

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?

With 0% schema description coverage, the description fails to explain any of the three parameters (uid, folder, account). It adds zero meaning beyond the schema structure, leaving the agent without guidance on how to populate inputs correctly.

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 'Add the \Flagged (starred) flag' clearly states the action and resource. It directly contrasts with the sibling 'unstar_email' which removes the flag, making the tool's purpose unambiguous.

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

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

No guidance on when to use this tool versus alternatives like 'unstar_email' or other email actions. The description lacks any context about recommended scenarios or prerequisites.

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 already indicate idempotentHint and destructiveHint, but the description adds no additional behavioral context (e.g., what happens if already unflagged). It merely restates the action without enhancing transparency beyond the 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 very short (one sentence), making it concise but insufficiently informative for a multi-parameter tool. It is front-loaded, but lacks structure or elaboration.

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 zero parameter coverage and no explanation of output or behavior, the description is incomplete for effective tool use. It does not leverage the existing output schema or add needed context.

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?

With 0% schema description coverage, the description fails to explain the parameters (uid, folder, account). No added meaning for any parameter, leaving the agent to rely solely on names and types.

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 states 'Remove the \Flagged flag', which clearly indicates the action of unstarring an email, aligning with the tool name 'unstar_email'. It is a specific verb-resource pair, but could be more explicit about it being an email flag.

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 on when to use this tool versus alternatives, such as 'star_email' for starring. The description lacks context about prerequisites or 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.