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

No annotations exist, so description must cover behavior. It does not state read-only guarantee, pagination, rate limits, or auth requirements, leaving gaps for a mutation-sensitive agent.

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

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

Two efficient sentences, front-loaded with purpose, 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?

Describes return values (sender, subject, preview) but lacks pagination, ordering, or error handling; minimally complete for a simple list 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 coverage is 100%, and description adds no extra parameter meaning beyond what schema already documents, achieving baseline adequacy.

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' and resource 'recent emails in an inbox', and distinguishes from siblings like 'get_email' (single email) and 'search_emails'.

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 alternatives are mentioned; it is implied for fetching recent emails but lacks a comparison to 'search_emails' or 'wait_for_email'.

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

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

No annotations are provided, so the description carries the full burden. It discloses that creation yields an email address and explains the addressing behavior. However, it does not mention potential side effects (e.g., is this a permanent action? Are there limits?) or authentication needs. The description is adequate but not exhaustive.

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 just two sentences, both front-loaded with the core purpose. It uses an example to illustrate the naming behavior, making it efficient and actionable with zero waste.

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 4 optional parameters, no required fields, and no output schema, the description covers the main return value (email address) and the two usage modes. It could mention whether creation is reversible or if there are limits, but overall it is sufficient 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.

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

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining how parameters like 'name' and 'org' combine to form a meaningful address, and how 'preferred' provides explicit local parts. This goes beyond the schema's dry descriptions.

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 creates a new email inbox and returns an @lobstermail.ai address. It distinguishes two modes: providing name/org yields a meaningful address, omitting them yields a random one. This specificity differentiates it from sibling tools like check_inbox or list_inboxes.

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

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

The description gives guidance on when to provide name/org versus omitting them for a random address, but does not explicitly compare when to use this tool over siblings like send_email or list_inboxes. The context is clear enough for an agent to decide, but a brief note on prerequisites or alternatives would improve it.

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

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

With no annotations, the description partially discloses behavior (soft-delete, grace period) but omits details like reversibility during grace period, impact on related data, and required permissions.

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

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

Two sentences, front-loaded with the action and key behavior. 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 simplicity (1 param, no output schema), the description covers the main behavior but lacks info on return value, error cases, and state during grace period.

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 adds no extra meaning beyond the parameter's schema description. The tool is simple, so a 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 action ('Soft-delete an inbox') and distinguishes it from permanent deletion by noting the grace period. The verb and resource 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?

No explicit guidance on when to use this tool versus alternatives. The description does not mention prerequisites or when not to use it, leaving the agent to infer.

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

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

No annotations are provided, so the description carries the full burden. It accurately describes a read operation ('Get account information') and implies no side effects. It lacks explicit mention of authentication requirements, but this is typically inferred for account tools.

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

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

The description is a single sentence of 10 words, highly efficient with no unnecessary information. It is front-loaded with the verb and resource.

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

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

No output schema exists, so the description must convey the return structure. It lists three fields (tier, limits, usage stats), giving a reasonable idea but not a complete specification. For a simple account info tool, this is adequate.

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

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

There are no parameters, so schema description coverage is trivially 100%. The description adds no parameter details, but none are needed. Baseline 4 is appropriate.

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

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

The description clearly states the tool gets account information and lists specific fields (tier, limits, usage stats). It is distinct from sibling tools focused on email operations, making the 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?

The description does not explicitly state when to use or not use this tool compared to siblings, but the sibling set (all email-related) makes the context clear. For a simple read tool, this implicit guidance is sufficient.

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?

Without annotations, the description discloses that it returns the full body in an LLM-safe format, which is a useful behavioral trait. However, it does not mention any other behaviors like authentication needs, rate limits, or side effects. It is adequate but not rich.

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 wasted words. It front-loads the action and key details, making it efficient and easy to parse.

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 only two required parameters and no output schema. The description explains the return format (full body in LLM-safe format), which is sufficient for a simple retrieval operation. It could mention the absence of pagination or filtering, but overall it is complete for this level of 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?

The input schema already provides complete descriptions for both parameters, including example formats (e.g., 'eml_...', 'ibx_...'). The description adds no additional meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.

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

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

The description clearly states the action (get), the resource (single email by ID), and a distinctive feature (LLM-safe format). It differentiates from siblings like search_emails or list_threads which retrieve multiple emails or threads.

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 use when you have an email ID, but does not explicitly guide when to use this tool versus alternatives like search_emails or list_threads for other scenarios. No exclusion criteria or sibling comparisons are provided.

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

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

No annotations are present, so the description should fully disclose behavioral traits. It only mentions the output content (sender, subject, preview) but does not address permissions, rate limits, or whether attachments are included. For a retrieval tool, this is insufficient.

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

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

Two concise sentences that front-load the main purpose and key output details. Every sentence adds value without 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 two-parameter retrieval tool with no output schema, the description adequately explains the return format (chronological order, sender, subject, preview). However, it could mention pagination or size limits for completeness.

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

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

The input schema has 100% description coverage with example formats for both parameters (ibx_..., thd_...). The description adds context about the output (chronological order, preview) but does not enhance parameter meaning beyond the schema.

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

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

The description explicitly states the tool retrieves a conversation thread with all emails in chronological order, including sender, subject, and preview. This clearly distinguishes it from siblings like get_email (single email) and list_threads (list all threads).

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 use when needing a full thread view but does not explicitly state when to use this tool over alternatives like search_emails or list_threads. No exclusions or prerequisites are provided.

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

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

With no annotations, the description states it lists active inboxes, implying a read operation, but does not disclose any behavioral details like pagination, limits, 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?

The description is a single, succinct sentence that is front-loaded with the verb and resource, containing no extraneous 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 parameters, no output schema), the description covers the essential purpose. It could mention the output format or that it returns a list, but it is sufficient for an agent to understand its basic function.

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 tool has zero parameters, so schema coverage is 100%. The description adds no parameter information, which is acceptable given no parameters exist.

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 (List) and resource (all active inboxes for this account), and it distinguishes from sibling tools like check_inbox (specific inbox) and create_inbox (creation).

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 get a list of inboxes) but provides no explicit guidance on when not to use or alternatives beyond what sibling names suggest.

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

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

With no annotations, the description carries the full burden and adequately discloses grouping logic and sort order (newest first). It does not contradict any 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?

Three concise sentences with no wasted words. First sentence states the action, second adds grouping detail, third adds ordering. Efficient and 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?

The description covers key behavioral aspects but does not describe the return structure of thread objects, which would help an agent understand what fields are available. Slightly incomplete.

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

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

Schema coverage is 100%, so the description adds no additional meaning beyond what the schema provides. Baseline score of 3 is appropriate.

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

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

The description clearly states the tool lists threads for a specific inbox, explains grouping by In-Reply-To/References headers or subject, and notes ordering. It distinguishes well from siblings like get_thread or list_inboxes.

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 you need to view threads in a given inbox, but does not explicitly mention when not to use it or alternatives like get_thread. However, the context and ordering info provide clear guidance.

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

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

With no annotations, the description partially covers behavior (matches on subject, sender, body preview; optional filters). However, it omits important traits like pagination, result ordering, return format (likely metadata only), or performance implications.

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 redundancy. Core operation stated first, optional filters listed second. Every word 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?

Given 8 parameters and no output schema, the description should explain return format, pagination, or empty result behavior. It mentions 'body preview' but doesn't clarify output structure, leaving gaps.

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

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

Schema coverage is 100%, providing baseline 3. The description adds value by summarizing filter capabilities and mentioning body preview matching, which goes beyond schema descriptions.

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 emails by keyword across inboxes, specifying match fields (subject, sender, body preview). It distinguishes from sibling tools like get_email or list_inboxes by focusing on cross-inbox keyword search.

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?

While the description implies usage for content-based search, it does not explicitly differentiate when to use this tool versus alternatives like get_email (for known IDs) or wait_for_email (for polling). No when-not-to-use guidance is provided.

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

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

With no annotations, the description must disclose behavioral traits. It mentions the account tier requirement and threading behavior, but does not address mutation side effects (e.g., sent folder, quotas) or error conditions. This is partial 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.

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

The description is two sentences, front-loaded with the main purpose. It is concise and avoids extraneous details, though a bulleted list could improve scanability for longer descriptions.

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 7 parameters and no output schema, the description covers the core action, a prerequisite, and a key parameter nuance. However, it does not explain return values (e.g., sent email ID) or error scenarios, leaving some gaps for an AI agent.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds minimal extra meaning beyond the schema: it reinforces that in_reply_to enables threading (already in schema) and notes body_html as optional (already implied by not being required). No significant new 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 action ('Send an email from an inbox') with a specific verb and resource. It also adds nuance by mentioning replying within a thread via in_reply_to. However, it does not explicitly differentiate from sibling tools like check_inbox or search_emails, which limits distinction.

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 prerequisite ('Requires a verified account (Tier 1+)') and explains a specific use case ('To reply within a thread...'). However, it lacks guidance on when not to use this tool or what alternatives exist among sibling 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?

The description discloses key behavioral traits: real-time server-side long-polling, near-instant return on arrival, and LLM-safe email format. This adds value beyond the absence of 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 three sentences with no wasted words. It front-loads the main action and follows with behavior and return format.

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?

Without an output schema, the description explains the return value (email body in LLM-safe format). It covers wait behavior, filtering, and result format, though lacks details on error handling.

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?

All parameters are described in the schema (100% coverage), so the description does not need to elaborate further. It merely references 'optional filters,' adding no extra meaning.

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 purpose: 'Wait for an incoming email matching optional filters.' It uses a specific verb-resource combination and distinguishes from siblings like check_inbox (non-blocking) and get_email (retrieving existing).

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 real-time waiting but lacks explicit guidance on when to use versus siblings or when not to use. No alternatives are named, leaving the agent to infer context.

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