Missed-call text-back for contractors: missed-call cost math, how it works, owners read their calls.
Scored across 4 tools
Each tool targets a clearly different intent: arithmetic modeling (estimate_missed_call_cost), product/pricing facts (how_ringback_works), the call log (my_missed_calls), and the text log (my_texts_sent). The two log readers are structurally similar but are unambiguously separated by resource (calls vs texts) in both name and description.
All names are snake_case and readable, but the conventions vary: a verb_noun pattern (estimate_missed_call_cost), an interrogative phrase (how_ringback_works), and a possessive 'my_' prefix for the two data tools. Recognizable, but not one predictable pattern.
Four tools is well within a sensible range for a narrow product-info plus read-only log server, and each has a distinct job. It is slightly thin, but nothing feels padded or redundant.
Coverage is read-only: pricing/facts, cost estimation, call log, and text log. There are no write operations — an agent cannot trigger a text-back, update a lead's status, or check account/trial/config state — which will cause dead ends for follow-up actions after a report.
Arithmetic on your own numbers: calls per week x missed % x close rate x average job value, per week, month and year, with every step and assumption shown. It is an estimate of the value of jobs at stake from missed calls, not a prediction of what any tool will recover. Also shows how many saved jobs a month would cover Ringback's price.
| Name | Required | Description | Default |
|---|---|---|---|
| calls_per_week | Yes | Inbound calls the business gets in a typical week. | |
| missed_percent | Yes | Share of those calls that go unanswered, in percent (e.g. 25). | |
| average_job_value | Yes | Average revenue per job, in US dollars. | |
| close_rate_percent | Yes | Share of answered callers who normally book a job, in percent (e.g. 30). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish this as a safe, idempotent, closed-world read. The description adds real behavioral context beyond them: the calculation is deterministic arithmetic with every step and assumption exposed, and the output is an estimate of jobs at stake rather than a forecast of recovered revenue. Disclosing that the response includes Ringback price coverage is extra transparency the annotations cannot convey.
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 formula is front-loaded and each sentence does work: calculation, then the estimate-vs-prediction caveat, then the Ringback price-coverage output. The third sentence leans slightly promotional and could be folded into the output description, but it is short and informative rather than wasteful.
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 carries the burden of explaining returns, and it does: per-week, per-month and per-year figures, shown steps and assumptions, plus a break-even framing against Ringback's price. It stops short of describing the response structure or formatting, which is a minor gap for a purely arithmetic 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%, so the baseline is 3, but the description earns an increment by stating how the four inputs combine (calls per week x missed % x close rate x average job value), which tells the agent the interaction semantics rather than just each parameter in isolation. Units, ranges and examples are already handled by 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 gives a specific verb and resource (arithmetic on the caller's own numbers producing a missed-call cost estimate) and spells out the exact formula and the periods returned. It also explicitly bounds the claim — value of jobs at stake, not a recovery prediction — which cleanly separates it from the sibling tools that report actual calls or texts.
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 context is clear: the caller must supply their own business numbers, and the result is a what-if estimate rather than a measurement. It does not, however, name when to prefer this over investigating real data via my_missed_calls, leaving that routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Facts about Ringback, missed-call text-back for contractors and home-service businesses: how the text is sent, phone requirements (Android, iPhone options), what the owner sees, price ($17/month or $170/year per business line), the 7-day free trial with no card, and what Ringback does not do.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds rich, actionable behavioral knowledge far beyond the annotations, including specific pricing models ($17/month), device requirements (Android/iPhone), trial details, and scope exclusions ('what Ringback does not do'). It does not contradict the readOnlyHint: true annotation.
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 highly dense and efficient, front-loading all critical information (cost, requirements, features, exclusions) into a single, structured paragraph.
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?
As a knowledge retrieval tool with no parameters, the description is exhaustive, covering functionality, cost, prerequisites, and limitations, making it complete for its purpose.
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?
Since the tool has zero parameters and 100% schema coverage, the baseline score of 4 is maintained, as the description correctly identifies the tool as static knowledge-providing.
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 identifies the precise resource (Ringback), the use case (missed-call text-back), and the target audience (contractors and home-service businesses), clearly distinguishing it from sibling tools focused on user data.
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 it does not explicitly state 'use this when...', the description is so comprehensive about the service's features, pricing, and limitations that it clearly dictates its appropriate usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the missed calls in your own Ringback call log for a time range: when, the caller's number, whether a text-back went out (and its delivery status) or why not (e.g. already texted recently, opted out, do-not-text), and the lead's status. Counts first, then up to 50 most recent calls. Needs a personal Ringback access token, created by the business owner in Ringback (Settings, AI assistants) and sent as "Authorization: Bearer ". Read-only; reads only that business's own call and text log.
| Name | Required | Description | Default |
|---|---|---|---|
| range | No | Time range: "today" (since midnight in the business's time zone), "7d", "30d" or "90d" (that many days back from now). Default "7d". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent and closed-world, but the description adds substantial behavior beyond them: the exact auth mechanism (owner-created token in Settings, AI assistants, sent as a Bearer header) and the return shape ordering (counts first, then at most 50 most recent calls), which warns the agent about truncation.
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?
Front-loaded with the core action and the returned fields, and the auth sentence, while long, is operationally necessary. It is dense but slightly overpacked, stacking output fields, auth setup and read-only scope into three long sentences.
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 correctly compensates by enumerating returned fields (when, caller number, text-back status or reason, lead status) and the result ordering. Auth prerequisites and the 50-record cap are also disclosed, leaving nothing critical missing for invocation.
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 single 'range' enum is fully documented in the schema, including the default. The description only mentions 'for a time range' and adds output-field meaning rather than parameter meaning, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Names a specific verb and resource ('List the missed calls in your own Ringback call log') and scopes it clearly to the caller's own log, which distinguishes it from siblings like my_texts_sent and estimate_missed_call_cost.
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?
Establishes the context of use (your own call log, read-only, requires a personal owner-created token) and implicitly rules out cross-business queries by saying it reads only that business's log. It stops short of explicitly naming a sibling as the alternative for related questions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the texts your Ringback line sent in a time range: missed-call text-backs, your replies from the dashboard and automatic replies, with delivery status as the phone reported it, the median time from call to text-back, and up to 50 most recent texts with their wording. Needs a personal Ringback access token, created by the business owner in Ringback (Settings, AI assistants) and sent as "Authorization: Bearer ". Read-only; reads only that business's own call and text log.
| Name | Required | Description | Default |
|---|---|---|---|
| range | No | Time range: "today" (since midnight in the business's time zone), "7d", "30d" or "90d" (that many days back from now). Default "7d". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations by disclosing the authentication model (personal access token created by the business owner under Settings, AI assistants, sent as a Bearer header) and the read scoping ('reads only that business's own call and text log'), which agents cannot infer from readOnlyHint alone.
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?
Front-loaded with the core action and scope, then content detail, then the auth prerequisite. It is a dense run-on sentence, but each clause (delivery status, median call-to-text-back time, 50-text cap, token requirement) carries real 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 compensates by describing what comes back: delivery status as reported by the phone, the median time from call to text-back, and up to 50 most recent texts with wording. Auth and read-scoping are also covered, so nothing needed for correct invocation is missing.
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 enum already documents each range value, so the description adds nothing about parameter semantics beyond restating 'in a time range'. Baseline 3 applies when the schema does the heavy lifting.
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?
States a specific verb and resource ('List the texts your Ringback line sent') and enumerates the content types (missed-call text-backs, dashboard replies, automatic replies), which clearly distinguishes it from the sibling my_missed_calls.
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 scope ('your Ringback line sent in a time range') makes clear when this tool applies and implicitly separates it from the missed-calls sibling, but there is no explicit guidance on when to prefer an alternative or what to do when the range is insufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
estimate_missed_call_costhow_ringback_worksmy_missed_callsmy_texts_sentMissed-call cost by trade, setup pricing, Google local presence and Pro Sites for contractors.
Verified pricing for 21 answering services & AI receptionists, dated weekly. Missed-call ROI calc.
AI phone receptionist for small businesses: read calls, leads and booked appointments.
Contractor operations on 3Bids: CRM, jobs, dispatch, estimates, invoicing, calls, and reports.
Add one secure layer between your agents and this server.
