RevDesk Product MCP

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

The annotations already mark the action as destructive and not read-only; the description adds the billing consequence and which account level is charged, giving useful context beyond the schema and 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 compact sentences cover what is done, how to supply the phone_or area choice, and that billing applies. Everything is front-loaded and none of the sentences repeat schema field descriptions verbatim.

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 and no guidance on edge cases, such as what happens if both phone_number and area_code are supplied or if neither is supplied. For a destructive, billing-incurring action, an agent needs a bit more about result and exceptional states than this description gives.

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 fully describes all three parameters, but the description adds the relationship between phone_number and area_code: exact value from search_available_numbers versus auto-pick by area. This value-add goes above the raw schema field 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?

States a specific verb, purchase a phone number, and its target account, so the resource and the action are unmistakable. It also distinguishes itself from search_available_numbers and list_phone_numbers by focusing on the actual buying step.

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?

Clearly instructs when to provide an exact number from search_available_numbers or when to give only an area code for auto-pick. It doesn't explicitly say which situations should not use the tool, but its intended usage context is concrete and actionable.

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 disclose read-only, idempotent, non-destructive behavior. The description adds a useful dynamic cue with 'current', telling agents that the returned status is the latest state and may change between calls. No contradiction with annotations was found.

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, front-loaded sentence that names the action, target, and differentiating factor without any filler. It earns its place entirely.

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 one-parameter, read-only getter with robust annotations, the description is nearly complete: the agent can infer that invoking get_call with a valid call_id returns status and details. It omits edge-case behavior such as handling of unknown call_ids, but that is a minor gap for such a simple tool.

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

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

Schema description coverage is 100%: the schema already documents call_id as the identifier from place_call or list_calls. The description only repeats 'by id' and does not add meaning beyond the schema, 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 states a specific verb ('Get'), a specific resource ('a single call'), and a clear dimension ('current status and details'). It distinguishes itself from sibling tools like list_calls (which retrieves multiple calls) and place_call/hangup_call (which act on calls rather than merely read them).

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 the usage context — use this when you need details for a specific call by id — but it does not explicitly address when to prefer a sibling tool such as list_calls. The schema's note that call_id comes from place_call or list_calls provides some provenance, but no direct when-to-use or when-not-to-use guidance 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 declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description only needs to add context beyond those. It adds a current-month rollup and which metrics are covered, but does not describe any caveats, such as whether data is near-real-time, delayed, or how the outputs are shaped. This 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?

One concise, front-loaded sentence states the resource, time scope, and outputs. Every word adds value, and the structure efficiently communicates the 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?

For a zero-parameter read-only rollup tool, the description is complete: it specifies the time window, the item being retrieved, and the metrics contained in the result. The annotations cover the safety profile, so no further context is necessary for an agent to invoke this tool appropriately.

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 zero parameters, so the description cannot add parameter meaning. The baseline for zero-param tools is 4; the description simply confirms the lack of inputs by being a standalone retrieval tool. Nothing about parameters needs explanation.

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 ('get') with a concrete resource ('current-month usage rollup') and enumerates the components (calls placed, minutes, active numbers, spend). This clearly differentiates from sibling tools that work with individual calls or numbers.

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 'current-month' qualifier and aggregate focus imply usage is for cumulative monthly statistics rather than for listing calls or performing actions. It does not explicitly name alternatives or exclusions, but context is clear enough for an agent to choose it over call-listing or SMS 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?

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false, covering the core safety profile. The description adds the 'in-progress' state requirement, which is useful, but it does not explain what happens if the call is already ended or a non-active call id is supplied.

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

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

A single sentence contains the action, the target state, and the locating mechanism, and all content is relevant. There is no redundant filler or boilerplate.

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, one-parameter mutation with a rich set of annotations, the description is nearly complete at the required level of detail. The only minor gap is the lack of behavioral details for already-terminal state or error handling, but this is partially covered by the 'in-progress' qualifier.

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% with the call_id description 'Call id of an active call,' so the schema fully documents the parameter. The description's 'by id' adds no additional semantics beyond what the schema already provides.

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 a specific verb ('hang up'), a resource ('in-progress call'), and the lookup key ('by id'). This differentiates it from siblings like place_call, get_call, and list_calls without needing to inspect schemas.

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?

'Hang up an in-progress call by id' gives clear context: this tool applies to active calls only, not to scheduled or completed calls. It does not explicitly name alternatives or exclusions, but the intended trigger state is obvious and sufficient for this simple action.

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, openWorldHint, idempotentHint, and non-destructive behavior, so no safety disclosure is needed. The description adds return content detail (CNAM display names) but does not describe pagination, sorting, or any other behavioral nuance. This 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, front-loaded sentence with no filler. Every word adds meaning: 'List', 'verified caller IDs', and 'CNAM display names' fully describe the operation.

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 zero-parameter, read-only list tool, the description is complete. The annotations cover safety and idempotency, and the description tells the caller what data is returned. No additional context such as auth requirements or output format is necessary for such a simple operation.

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 and the schema has 100% coverage, so there is nothing to explain. The description is not required to add parameter semantics, and the baseline of 0 params 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 states a clear action ('List') and a specific resource ('verified caller IDs'), and it adds the detail that CNAM display names are included. It is easily distinguishable from the sibling list_phone_numbers because caller IDs and phone numbers are different resources.

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 explicit guidance on when to use this tool versus alternatives such as list_phone_numbers or get_call. There is no when-to-use or when-not-to-use context beyond the resource name itself, so usage context must be inferred from the tool name.

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 annotations already carrying read-only, idempotent, and non-destructive hints, the description adds meaningful behavioral context: results are ordered most recent first, and the response includes specific fields. This goes beyond the schema and annotations without contradicting them.

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 short and front-loaded: the primary action is in the first two words, followed by field information and ordering. Every sentence is useful with zero filler or 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 simple list call with two optional parameters and no output schema, the description supplies the output field names, ordering, and overall scope. The schema documents the limit and status filters, 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 descriptions cover 100% of the parameters (limit and status), so the parameter semantics are already fully captured in the schema. The description does not add new parameter meaning, but it also doesn't need to; a 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?

The description clearly states the action ('List recent calls') and the resource (call history), with useful specifics about included fields (status, duration, cost) and ordering. It does not explicitly mention sibling tools, but the verb 'list' and phrase 'recent calls' make the distinction from get_call/get_usage apparent.

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 intended use is implied: call this when you want a list of recent calls. However, there is no explicit guidance about when to prefer get_call for a single call or get_usage for aggregated usage, and no alternatives are named. This is adequate but leaves some routing to the agent.

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 annotations already provide readOnlyHint and destructiveHint=false, so the description does not need to restate safety. It adds useful behavioral context by qualifying the scope as account-owned numbers and clarifying their role as possible 'from' numbers, going beyond what the schema or annotations express.

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 leads with the verb and resource, uses a parenthetical to add important semantic context, and contains zero filler or repetition of the title.

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, a lightweight input schema, and no output schema, the description is complete enough for an agent to invoke the tool correctly. It states what is returned and what the result is for, so no critical context 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?

The tool has zero parameters, so the description is not burdened to explain parameter meaning. The baseline for 0-parameter tools is 4, and the description does not introduce any conflicting or unnecessary parameter 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 uses a clear verb and resource — 'List the phone numbers' — and adds ownership scope ('owned by this account') plus intended usage ('usable as from numbers'). This distinguishes it from sibling tools such as search_available_numbers and buy_phone_number.

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 makes the usage context clear: use this tool when you need this account's owned phone numbers for the 'from' field. It does not explicitly say when not to use it or compare against list_caller_ids, so it stops short of a 5.

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 signal the action is non-read-only and destructive. The description adds genuinely useful behavioral detail: the call is bridged server-side and no audio flows through the AI, plus it returns a call id for status checks. It stops short of explaining call-failure or recording behavior, so not a 5.

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. The core action is front-loaded, and the following detail (server-side bridging and return value) is useful rather than filler.

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 is enough to select and invoke the tool with no output schema present: it explains the main purpose, the required source/destination, the returned call id, and a key behavioral property. It could go further on side effects like call failure or recording, but the schema covers recording defaults.

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 schema already documents the parameters. The description adds a valuable constraint by saying 'from_number' must be one of the account's RevDesk numbers. This is slightly helpful, but the schema is strong.

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 states a specific verb and resource: 'Place an outbound phone call' from an account RevDesk number to a destination. It is clearly distinguishable from sibling tools like send_sms, get_call, and hangup_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?

It clearly frames when this tool is appropriate: for outbound calls from an account number. It also implies the returned call id is used with status-check tools. It does not explicitly mention exclusions or alternative tools, but the purpose statement provides enough 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?

Annotations already establish the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false) and the description does not contradict them. The description adds useful scope context ('available for purchase' and the allowed search filters), but it does not disclose operational behavior such as whether already-owned numbers are excluded or whether availability changes between calls. Given annotations cover safety fully, a 3 is appropriate.

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

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

A single 12-word sentence front-loads the verb and resource, then adds the two relevant filter dimensions. There is no filler, no repetition of schema details, and no parenthetical clutter — every phrase earns its place.

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

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

For a read-only search tool with a complete four-parameter schema and annotations covering safety, the description is nearly sufficient. What is missing is workflow context: it does not say that a found number can be purchased via buy_phone_number or that list_phone_numbers returns numbers you already own, so the agent must infer the tool's place in the sales flow.

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% and every parameter already has inline documentation, including defaults (limit default 10, country default US) and validation patterns (area_code matches ^\d{3}$). The description repeats 'area code or phone number' without adding semantics beyond what the schema provides, 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?

The description uses a specific verb ('search') and a specific resource ('phone numbers available for purchase'), and states the two filtering dimensions ('by area code or digit pattern'). It implicitly distinguishes itself from siblings like list_phone_numbers (owned numbers) and buy_phone_number (the purchase action), but it never names a sibling explicitly, so the differentiation is left to inference rather than stated.

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 phrase 'available for purchase' implies the use case — searching look for numbers you don't yet own, before executing buy_phone_number — but this is implied rather than stated. There is no explicit guidance on when NOT to use it, e.g. 'use list_phone_numbers to view numbers you already own' or 'use buy_phone_number afterwards to purchase a result with digit pattern.'

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 signal a side-effecting operation via readOnlyHint=false and destructiveHint=true, so the description does not need to restate that. It adds the E.164 requirement and lookup tip, but does not disclose other important behaviors such as costs, error conditions, or delivery confirmation. It extends the annotations only moderately.

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 concise sentences with no filler. It front-loads the core action and gives a practical prerequisite for correct invocation.

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, fully-required 3-parameter tool, the description covers the message, source number validation, and destination format. It does not describe return values or status confirmation, but no output schema is provided and the operation is otherwise straightforward enough 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 description coverage is 100%, so the schema already documents the parameters. The description reinforces the E.164 format and points to list_phone_numbers for a valid sender, but it does not add substantial meaning beyond what the schema already provides.

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 and resource: 'Send a text message from one of the account's RevDesk phone numbers.' This distinguishes it from siblings like place_call and list_phone_numbers, so an agent can identify it as the SMS-sending tool.

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 a clear prerequisite: use list_phone_numbers to find a valid 'from' number. It also positions the tool as the way to send text messages. It does not explicitly mention exclusions or contrast with voice call alternatives, so it misses the highest bar for usage guidance.

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