Call Me

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the action (rings iPhone), the timeout (~30s), the special nature of the 'to' number (not a real phone number), the meaning of session_token, and the conditional "ringing" status requiring polling. This is rich, honest behavioral context beyond the schema.

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, front-loaded with purpose, then timeout behavior, then parameter clarifications. Every sentence adds meaning and there is no repetition of schema information. It is appropriately concise and well-structured.

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

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

The tool has no output schema, so the description must hint at return behavior. It mentions the 'ringing' status and the need to poll. It covers the core action, the special 'to' number, and session continuity. However, it does not mention failure modes (e.g., unanswered call, invalid number) or the exact return format beyond 'status', which could be useful for a complex, higher-risk 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 0%, so the description must compensate. It explains 'to' in detail and clarifies 'session_token' usage, and 'question' is implied by 'speak the question aloud.' However, 'from_label' is left entirely unexplained. Thus it covers about half of the parameters, which is partial compensation for the missing 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 immediately states the tool's core function: 'Ring the human's iPhone, speak the question aloud, and return what they say.' This is a specific verb+resource pair that clearly distinguishes it from sibling tools like text or poll_result, which handle different communication modes or follow-ups.

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 instructs what to do if the result status is 'ringing': 'follow up with poll_result.' It also advises passing a session_token to maintain the same thread. While it doesn't explicitly contrast with text or set_thread_title, the follow-up guidance and context for the call scenario are 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?

With no annotations, the description carries the burden and it discloses that the tool waits up to ~25 seconds, settles on answer/decline/timeout, and returns a transcript. It does not mention error handling or repeated polling, but the core blocking and outcome behavior is transparent.

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 entire description is a single, front-loaded sentence that avoids filler. Each clause adds specific behavioral or outcome information, making it highly concise and well-structured.

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

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

For a simple polling tool with no output schema, the description adequately covers purpose, wait duration, terminal outcomes, and return content. It omits parameter-specific semantics and error cases, but the main usage context is fully delivered.

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

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

The schema has 0% description coverage, yet the description never explains call_id or session_token. Although the names are intuitive, the description adds no detail about their role or format, so it fails to compensate for the low schema coverage.

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

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

The description uses a specific verb ('Check on') with a clear resource ('a call that was still ringing') and explains the outcome (final status and transcript). This clearly distinguishes it from sibling tools like call or wait_for_reply, as it is the polling step for a ringing call.

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 it: after a call has been initiated and is still ringing, and it covers expected terminal events. It does not explicitly name alternatives or state exclusions, such as comparing to wait_for_reply, but the context is clear.

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

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

No annotations are provided, so the description must disclose behavioral traits. It only states the thread title is 'shown in the app', but does not mention overwrite behavior, permissions required, or any side effects. For a mutation 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?

The description is two sentences with no redundant wording. It front-loads the action and provides a concrete example in the same sentence, making it easy to scan.

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

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

The tool is simple and the description covers the core action, but it lacks essential context for a complete call: no explanation of the session token, no mention of idempotency or overwriting, and no guidance on how to retrieve the thread. Given the simplicity, a 3 is appropriate—adequate but with clear informational 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%, so the description must document the parameters. It implicitly refers to 'title' but does not explain 'session_token' at all. There is no mention of format, requirements, or how to obtain the token, leaving significant 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 uses the specific verb 'Name' and clearly identifies the resource as 'this session's conversation thread on the human's phone'. It also gives an example ('project or task'), which distinguishes it from sibling tools that handle calls or messages.

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

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

The description conveys when to use the tool: when working on a project or task, you can name the thread. It does not explicitly mention alternatives or exclusions, but no sibling tool serves this purpose, so the usage context is clear enough.

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 does disclose key behavioral traits: one-way, push notification, no ring, and thread continuity via session_token. However, it omits potential errors, permissions, rate limits, or what happens after sending, so it is not fully transparent.

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

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

The description is only two sentences, front-loaded with the core action and followed by essential parameter clarifications. There is no redundant or verbose language.

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 moderate complexity (4 params, no output schema) and no annotations, the description covers the main purpose and key parameters but lacks information on return values, error handling, and explicit relationship to sibling tools. It is adequate but not fully complete for an 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?

The schema has 0% per-parameter description coverage, so the description must compensate. It explicitly clarifies the 'to' parameter (10-digit /call-me number) and the 'session_token' parameter (stay in the same thread). 'body' is self-explanatory, but 'from_label' is not described, leaving a partial gap.

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 'Send a one-way text to the human's phone' with a specific verb and resource, and distinguishes it from siblings by contrasting 'push notification, no ring' with a call. This leaves no ambiguity about the tool's function.

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

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

The description provides some context (one-way, push, no ring) and explains the 'to' and session_token parameters, but does not explicitly mention when to use this tool versus alternatives like call or wait_for_reply. The 'one-way' wording implies not for two-way interactions, but this is not stated as a clear exclusion.

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

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

With no annotations provided, the description carries the full burden. It discloses the long-polling behavior ('Long-polls up to wait_s (max 30s)'), the return shape ('{events, cursor}'), cursor semantics for incremental reads, and how empty events should be interpreted. This is far beyond a minimal statement.

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, front-loaded with the core purpose and followed by essential mechanics and usage. There is no filler; every clause contributes necessary 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?

With no output schema, the description appropriately explains the return value as {events, cursor} and hints at event content ('texts and voicemail transcripts'). It covers purpose, usage, behavior, and return for a simple polling tool, but could be more explicit about the exact event object structure and error handling, leaving it at 4.

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

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

The schema has zero parameter descriptions (0% coverage), so the description must compensate. It explains 'wait_s' (max 30s), 'cursor' (pass the returned cursor), and 'session' implicitly through 'this session'. However, 'session_token' is not explicitly described, and the event structure is only partial, so 4.

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: 'Wait for the human to send something back to this session.' It distinguishes from siblings by specifying 'texts and voicemail transcripts arrive here' and positions itself as a polling tool via 'Long-polls' and 'poll again,' unlike call or text.

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 usage context: 'Pass the returned cursor next time to only see new events' and 'poll again if you are still waiting.' It implies the tool is for when a human reply is expected, but does not explicitly name alternatives or exclusions, so 4 rather than 5.

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