Pinpoint dealership sales tools

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

ReadOnlyHint already marks it safe; the description adds its own caveat that it is general information, not legal advice, and enumerates exactly what the tool returns (disclosure rule, consent rule, statute, federal baseline, script). No hidden mutations or side effects are implied and nothing contradicts the 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 front-loads the key subject and lists contents compactly after a colon, with no filler. The first sentence is long and could be split, but every element 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 lookup tool with no output schema, it explains not just what question it answers but the exact fields returned and the federal/state scope. It doesn't say what happens for invalid states or missing company, but that is secondary for selection and 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%: both state and company are described in the schema. The description adds no parameter-level detail beyond that, so the schema carries the burden; 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 clearly identifies the resource (state-specific AI caller disclosure rules), the trigger contexts (answering missed calls or placing outbound calls), and the output contents. It does not use an explicit verb like 'retrieve' or 'return', and it doesn't explicitly separate itself from answer_ai_caller_question, so it stops short of a 5.

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 concrete when-to-use context: when an AI voice assistant answers missed calls or places approved outbound calls, and it scopes the lookup to US states. It doesn't name alternatives or state when not to use it, but the context is clear enough 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 provide readOnlyHint and openWorldHint, so the description only needs extra context. It adds that the result is general information rather than legal advice, is scoped to one US state, and draws on the federal baseline and state entry. This is useful behavioral context and does not contradict 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 two sentences, front-loaded with the main action and scope. The phrase 'from the federal baseline and the state entry' is somewhat cryptic but compact, and the disclaimer 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 simple two-string Q&A tool with read-only/open-world annotations, the description covers the domain, geographic scope, and non-legal nature of the answer. It is missing explicit sibling routing and output-shape hints, but those are more relevant to other dimensions.

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 must compensate for the two parameters. It clarifies that state refers to a US state and question concerns AI voice assistants, adding meaning beyond the bare schema. Still, it leaves the accepted state format/values and expected question phrasing unspecified.

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 action ('Answers a question') and a precise domain: an automated/AI voice assistant handling missed calls or approved outbound calls in one US state. This clearly differentiates it from siblings like answer_recording_question and ai_caller_disclosure by topic and scope.

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 tool is for state-specific informational questions about AI-caller practices, and 'not legal advice' sets a boundary. However, it never names alternatives or states when not to use this tool, so sibling selection is left to inference.

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 and openWorldHint, lowering the burden. The description adds meaningful context: the answer is drawn from 'the state's consent entry' and is 'general information, not legal advice,' which tells the agent about sourcing and the limits of the answer. 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?

Two short sentences with no filler. The primary action and scope are front-loaded, and the disclaimer earns its place in the second sentence. Nothing could be removed without losing 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 simple two-string-parameter Q&A tool with no output schema, the description covers purpose, source, and output caveat. However, it leaves parameter formats and sibling-tool routing unaddressed, so it is adequate but not fully 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?

Schema description coverage is 0% and the description does not specify the expected format for 'state' (e.g., full name vs. abbreviation) or the scope of 'question' beyond the general topic. For an agent to invoke this tool correctly, some parameter guidance is needed and is currently missing.

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 ('Answers'), a specific resource ('question about recording phone calls in one US state'), and a specific data source ('from the state's consent entry'). It is clearly distinct from siblings like answer_ai_caller_question and call_recording_consent, and the 'General information, not legal advice' qualifier adds useful scoping.

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 the tool (a sales manager has a question about recording calls in a state) but provides no explicit when-not-to-use guidance or comparisons to sibling tools. The 'not legal advice' line is a caveat about output nature, not a usage exclusion, so the guidance is only implicit.

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 this read-only and closed-world; the description adds useful behavioral context by listing what the lookup returns and by adding a trust disclaimer ('General information, not legal advice'). It also confirms the closed scope ('All 50 states and DC') without contradicting any 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 packs the core purpose and output contents into a single front-loaded sentence, followed by two short scope/disclaimer sentences. It is compact and every clause adds 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 3-param, no-output-schema read tool, the description tells the agent what content to expect (consent rule, statute, sales note, notices), the coverage scope, and a caveat. It could be more explicit about optionality of rep/company, but the schema already covers that.

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 the schema already explains state, rep, and company. The description does not add meaning beyond the schema, so the 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 identifies the resource—US state call-recording consent rules—and enumerates the returned content (statute, sales note, notices). It lacks an explicit verb and doesn't name a sibling for differentiation, but the title and scope ('All 50 states and DC') make the function unmistakable.

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 implies the tool is for sales teams needing state-specific consent rules and ready-to-use greeting/outbound/text notices, and it cautions that it is general info rather than legal advice. It does not explicitly state when to prefer this over siblings like answer_recording_question or ai_caller_disclosure.

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=true, so the description does not need to restate safety. It adds useful content-level context by listing the groups, scoring rules, and four-minute review method. However, it does not disclose what actually happens when the tool is invoked, such as whether it returns a static reference or a formatted card.

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; the key identifying phrase 'eighteen-item pass-or-fail scorecard' comes first. It is concise, though the trailing list of groups and methods is packed together and could be slightly clearer.

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, no-output-schema tool, the description conveys the main content and purpose, which is reasonably complete. Still, it never explicitly states that invoking the tool returns the scorecard or how the agent should use the returned information, and it lacks any mention of how this relates to the sibling scoring tools.

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 has no parameter burden to carry; the baseline of 4 applies. No input-schema information is missing or in need of clarification.

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 identifies the resource as an eighteen-item pass-or-fail sales-call scorecard and enumerates its content (five groups, scoring rules, review method). It goes well beyond the bare title, so an agent can tell this is the reference scorecard rather than an action like score_call. However, it lacks an explicit verb such as 'returns' or 'provides', so it is not a full 5.

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 no guidance about when to use this tool versus alternatives like score_call, roleplay_card, or conversation_signals. It says the scorecard contains scoring rules, but it never states conditions such as 'when you need the scorecard criteria, use this; when scoring a call, use score_call.'

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=true and openWorldHint=false. The description adds that it runs without an AI model, is deterministic, and returns a structured score, flags, fixes, and a template example—richer than annotations 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?

Two sentences, no fluff, with the core purpose and rule list front-loaded, followed by usage guidance. Every sentence 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 single-parameter read-only tool with no output schema, the description fully explains behavior, return value structure, and how to select between this and the sibling. Nothing an agent needs 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 input schema has 100% coverage for the single 'text' parameter with a clear description. The tool description adds no extra parameter semantics, so the baseline of 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?

States a specific verb 'check' plus resource 'appointment ask' and enumerates the six fixed rules. It explicitly contrasts with review_appointment_ask, so an agent can immediately tell them apart.

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 says 'Use this for repeatable rule-based scoring; use review_appointment_ask for contextual AI feedback and a tailored rewrite.' This gives clear when-to-use and the alternative.

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=true, so the safety profile is known. The description adds that it 'Returns what passed, what failed and why', disclosing the output format and diagnostic nature, which goes beyond the annotation and helps the agent set expectations.

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, information-dense sentence that front-loads the core purpose and then lists the eight criteria. It is efficient with no fluff, though the long enumeration could be broken into a structured list for readability. Overall it 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 single-parameter read-only tool, the description is complete: it explains the eight evaluation criteria and the nature of the output. It doesn't address edge cases or error handling, but those are unlikely to be critical given the simplicity. No output schema exists, so the description reasonably covers what is returned.

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 covers the single parameter 'text' with a clear description ('The text message as it would be sent'), so baseline is 3. The tool description doesn't add further parameter-specific detail, but it does explain what the tool does with the input, which is sufficient given the high 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 states a specific verb ('Checks') and a precise resource ('sales follow-up text message') and enumerates eight distinct practices it evaluates. This clearly distinguishes it from sibling tools like write_follow_up_texts or rewrite_follow_up_text, which generate text, making its 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 implies a clear use case: to evaluate an existing text against best practices. While it doesn't explicitly name alternatives or state when not to use it, the contrast with generation siblings is evident from the wording, so an agent can infer the appropriate 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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is known. The description adds behavioral value by disclosing the conditional return behavior (list vs. detailed breakdown) and the specific sections included in the detailed response (sounds like, why it matters, what to do next, how to coach, how to practice). 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 tightly written sentences with no filler. The opening sentence establishes the tool's scope and grouping, and the second immediately explains the dual-mode behavior. 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?

For a read-only reference tool with one optional parameter and no output schema, the description is comprehensive. An agent knows exactly what to expect in both invocation paths and has no critical missing information needed to call it 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?

The schema covers the single parameter fully ('A signal slug from the list'), so the baseline is 3. The description enriches this by explaining the behavioral difference when the parameter is omitted versus provided, which goes beyond static schema documentation.

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 is a library of 40 sales moments grouped into six named categories, with two explicit modes: returning the full list when no signal is provided, or returning detailed guidance for a specific signal slug. This distinguishes it from action-oriented sibling tools like answer_ai_caller_question or score_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?

Usage is implied through the description of behavior: an agent can infer to call this when needing signal definitions or reference material. It explicitly explains both invocation modes (with/without the optional signal parameter), providing clear context, though it does not name alternative tools or exclusion criteria.

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=true, so the description need not restate that it is read-only. The description adds behavioral context: it is a reference/checklist that provides five sections, an example, and misleading lead statuses. It does not describe any side effects, which is consistent with readOnlyHint. It could add more detail about what the tool returns (e.g., a checklist, an example, a list of statuses), but the description is not contradictory and adds some value 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?

The description is a single sentence that front-loads the core purpose ('what a complete CRM note carries') and then lists the key components (five sections, example, misleading lead statuses). It is concise and structured, though it is a bit dense and could be split into two sentences for readability. 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?

For a zero-parameter, read-only reference tool with no output schema, the description is fairly complete: it tells the agent what the tool covers and why it matters (misleading lead statuses). However, it does not specify the exact five sections or the format of the output, which an agent might need to know to decide if this tool answers a specific question. Given the tool's simplicity, this is adequate but not fully 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?

The tool has zero parameters, so the schema is empty and schema description coverage is 100% by default. The description does not need to explain parameters. It explains the content of the tool's output/reference material, which is the only meaningful semantic content. Baseline 4 for zero-parameter tools 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 resource ('a complete CRM note') and a clear purpose: to convey what a complete CRM note carries after a sales call or text thread, in five sections, with an example and lead statuses that mislead managers. It is not a tautology and distinguishes itself from siblings like score_crm_note (which scores a note) and write_follow_up_texts (which writes texts). It could be slightly clearer about whether it is a reference/checklist tool versus an action tool, but the verb 'carries' and the structure imply a reference/educational 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 implies usage: it is a reference for what a complete CRM note carries, useful after a sales call or text thread, and it warns about lead statuses that mislead managers. However, it does not explicitly state when to use this tool versus alternatives like score_crm_note or conversation_signals. The context is clear enough for an agent to infer it is a reference/checklist, but there is no explicit when/when-not 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?

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered; the description usefully adds that it resolves aliases and falls back to closest matches rather than failing on an inexact term. That fuzzy-match fallback is behavior an agent could not derive from 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 tight sentences lead with what the tool returns, then cover alias handling and fallback behavior. No filler, nothing redundant.

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 lookup with no output schema, the description covers what is returned (matching or closest terms) and its alias tolerance. It stops short of describing ambiguous-match behavior or handling of unmatched input beyond 'closest matches', a minor gap.

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% for the single `term` parameter, so the baseline is 3. The description restates that a term, an alias, or a word inside a term is accepted, which essentially mirrors the schema wording and adds no new syntax or constraints.

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: it returns plain definitions from the Pinpoint sales conversation glossary of 92 terms, and even names the term range. No sibling tool does glossary lookup, so it is clearly distinguishable.

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 use case (looking up sales-conversation terminology) is implied by the resource name and the enumeration of terms, but there is no explicit statement of when to reach for this tool versus siblings or when it is not appropriate. Adequate but leaves routing to inference.

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 declare readOnlyHint=true and openWorldHint=false, so the description builds on that by detailing what the response contains and the precedence rule for whenLabel over legacy day values. It also notes that names are filled in, which clarifies the effect of the rep/company/customer parameters. 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?

The description is a single sentence with an embedded list, efficiently conveying the tool's purpose and output. It is not overly verbose, though it could be split for readability. 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 there is no output schema, the description carries the burden of explaining the response, which it does by listing the components (timing, channel, purpose, message, reply). It explains the anchoring behavior and precedence. However, it does not mention how optional parameters are handled when omitted, nor the exact response structure (e.g., JSON format). Overall, it is adequate for a read-only 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?

All parameters are described in the schema (100% coverage), so the description adds little beyond the schema. It references startLabel and whenLabel which are not parameters, but that clarifies behavior rather than parameter semantics. The description does not elaborate on the meaning of situation or day_and_time 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 clearly states the tool returns a follow-up sequence for a sales situation, enumerates the eight situations it covers, and specifies the content of the sequence (timing, channel, purpose, message, reply). This distinguishes it from related tools like write_follow_up_texts by focusing on the cadence rather than individual 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?

The description provides no guidance on when to use this tool versus siblings such as write_follow_up_texts, check_follow_up_text, or tailor_follow_up_cadence. It only explains how to anchor the sequence, not when to choose it. An agent would have to infer usage from the name and schema.

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 the tool as readOnly and openWorld, and the description adds meaningful context by explaining it uses a configured AI assistant (which explains the openWorld trait) and disclosing the prose output format. It does not cover failure modes or latency, but the annotations lower the burden.

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, each adding unique value: the core operation, the sibling differentiation, and a hard prerequisite. The main action is front-loaded with no 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 covers the core operation, output structure, alternative tool, and availability prerequisite. The main omission is clarifying how 'in context' is populated given that the schema only accepts 'ask', but this is a minor gap for a one-parameter tool with no output schema.

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 must compensate for the sole 'ask' parameter. It does clarify that the parameter is 'one appointment ask from a sales call' and contrasts it with check_appointment_ask, but it does not explicitly state the expected format, source, or how 'in context' is supplied, leaving some inference to 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 states a specific verb ('review') with a precise resource ('one appointment ask from a sales call') and enumerates the output components. It also explicitly distinguishes itself from the sibling 'check_appointment_ask', so an agent can tell the tools apart without inspecting 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?

The description gives direct selection criteria: 'Choose this for phrasing and coaching; use check_appointment_ask for deterministic six-part scoring and a fixed template example.' It also states the precondition that the tool is 'Available only when an assistant provider is configured.'

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=true and openWorldHint=true, indicating a safe, read-only transformation. The description adds that the tool checks and rewrites the text, which is consistent. It does not disclose details like whether the original meaning is preserved or how output is returned, but annotations cover the safety profile.

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 with zero waste. The core action is front-loaded, and every word adds value. It conveys what the tool does in a highly efficient manner.

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 tool with one string parameter and annotations covering safety, the description is adequate. It does not describe the output format or what the eight practices are, but those may be covered by sibling tools (e.g., check_follow_up_text). With no output schema, an agent might still wonder what exactly is returned, so completeness is moderate.

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 a single parameter named 'text'. The description clarifies that the text is a 'follow-up text' and that it will be checked against practices, adding meaning beyond the raw schema. However, it omits any constraints or format expectations, which would be more helpful given zero 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 specifies a concrete action (rewrites a follow-up text) and a distinguishing detail (against eight practices). It differentiates from siblings like check_follow_up_text (which only checks) and write_follow_up_texts (which writes from scratch) implicitly through the verb 'rewrites', but it does not explicitly name alternatives.

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: the tool is for rewriting an existing follow-up text so it passes eight practices, which suggests using it when you already have a draft. However, there is no explicit statement about when to use this versus check_follow_up_text or write_follow_up_texts, nor any mention of prerequisites 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?

The annotations already indicate readOnlyHint=true, and the description does not contradict that. It adds meaningful behavioral context by detailing exactly what the card contains: customer opening line, wants/fears, tells, objection phrasing, rep goal, strong answer characteristics, and feedback checklist. This goes beyond the structured annotations and helps the agent understand the tool's output shape.

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 front-loaded with the core purpose, but it is a long, dense single sentence with many embedded clauses and parentheticals. It contains useful information, yet it could be broken into clearer sentences or bullet-like structure. It is not bloated with filler, but it is less concise than it could be.

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 two-parameter card generator with a read-only annotation, the description covers the essential content of the card and the two selection dimensions. It does not describe the exact return format, but the enumerated contents give the agent a strong mental model. The lack of an output schema is partially mitigated by the detailed content list.

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, and it does: it names both parameters and gives concrete examples for each ('from the price shopper to the callback who went quiet' and 'from "I need to think about it" to "just email me the numbers"'). It also communicates the cardinality of each enum. It does not define every enum value, but the enum keys are already fairly self-explanatory.

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 identifies the tool as a practice card for sales roleplay and enumerates its contents, so an agent can tell it is a training/generation tool rather than a live-call tool. It lacks an explicit verb like 'generates' or 'returns', but the noun phrase 'A practice card' is unambiguous. It is distinguishable from siblings such as call_scorecard or write_follow_up_texts by its roleplay focus.

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 'practice card for a sales roleplay' implies when to use it, but there is no explicit guidance on when not to use it or which sibling tool to choose instead. An agent must infer that this is for training scenarios, not for live calls or follow-up writing. No alternatives or exclusions are named.

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=true and openWorldHint=true, so the read-only nature is covered. The description adds value by disclosing the output behavior: per-item pass/fail/not observable with evidence and a coaching note. It does not contradict the annotations; openWorldHint is vague but not contradicted. The description provides useful behavioral detail beyond the annotations, warranting a 4.

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, well-structured sentence that front-loads the core action and then specifies the output details. No redundant phrasing or filler. Every word contributes to clarity.

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 one parameter and no output schema, the description is complete. It specifies the input type, size limit, and the exact nature of the output (per-item scoring with evidence and coaching note). An agent has enough to call it correctly without additional 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?

Schema coverage is 100% – the parameter 'transcript' is described as 'Transcript, notes or a summary of one call, up to 6,000 characters'. The description reinforces the input type and adds the constraint that it must be for 'one call', which the schema does not explicitly state. This goes slightly beyond the schema, so a 4 is justified.

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 ('scores'), a clear resource ('sales call transcript, notes or summary'), and the exact scoring standard ('eighteen-item sales call scorecard'), plus the output granularity (pass/fail/not observable per item with evidence and coaching note). It clearly distinguishes from sibling tools like score_crm_note, which targets CRM notes, and call_scorecard, which likely defines the scorecard itself.

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 clearly implies when to use it: when you have a sales call transcript, notes, or summary to score. It does not explicitly name alternatives or exclusions, but the input scope is unambiguous given the sibling context. A 4 is appropriate because context is clear but no explicit 'when not to use' or alternative routing 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?

The description discloses the dual behavior of scoring and rewriting, which adds context beyond the readOnlyHint annotation. However, it does not clarify whether the original note is modified or a new version is returned, and it doesn't explain how the score is delivered. Given the annotations already indicate read-only behavior, the description should clarify the output format but remains ambiguous on this point.

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, well-structured sentence that leads with the primary action ('Scores') and efficiently conveys the full behavior. There is no fluff or redundancy, making it easy for an agent 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?

The tool has no output schema, so the description must explain what the tool returns. The description says it 'scores' and 'rewrites', but it doesn't explicitly state whether the return value is the rewritten note, a score, or both. This ambiguity leaves the agent uncertain about the expected output, making the definition incomplete for correct 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?

With 0% schema description coverage, the description must compensate. It provides context that the 'note' is a CRM note written after a sales call or text thread, which adds meaning beyond the schema's bare 'string' type. However, it doesn't specify the expected structure, length, or what constitutes a 'complete note', leaving some semantic 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 tool's action: it scores a CRM note and rewrites it with brackets for missing facts. The verb+resource is specific, and the purpose is unambiguous. However, it does not explicitly differentiate from sibling tools like crm_note_checklist, which might have overlapping functionality, so it misses the opportunity to distinguish itself.

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 mentions the context 'after a sales call or text thread' but provides no explicit guidance on when to use this tool versus alternatives. There is no mention of exclusions, prerequisites, or when another tool would be more appropriate. The agent is left to infer usage from the description alone.

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 read-only and open-world behavior, so the bar is lower. The description adds a useful behavioral fact—the existing days, times, and channels are preserved while every step is rewritten—without contradicting the readOnlyHint, since the rewrite appears to be a generated output rather than a persisted mutation. It does not disclose other traits like output format, but the annotations carry the main safety profile.

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 front-loaded sentence with no filler; every phrase adds information ('every step', 'keeping the days, times and channels'). It is appropriately compact for what it conveys, though some of that brevity explains why parameter coverage is thin.

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?

This tool has 7 parameters, low schema coverage, and no output schema, yet the description is the only source of guidance for most of them. It does not say what the tool returns, what the situation enum values mean, or how day_and_time and customer_first_name relate to the output, so an agent has to infer too much before calling it.

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 14% ('customer' is the only described property), so the description must compensate. It clarifies that 'customer' is the person to tailor for and implicitly ties 'days, times and channels' to cadence scheduling, but it leaves rep, company, product, customer_first_name, and the situation enum values unexplained.

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 action ('rewrites every step') on a clear resource ('a situation's follow-up cadence'), with the tailoring target ('for the customer you describe') and a preservation constraint ('keeping the days, times and channels'). This distinguishes it from siblings like rewrite_follow_up_text or write_follow_up_texts, which operate on individual texts rather than the whole cadence.

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 use case—personalizing an entire follow-up cadence to a described customer—but never states when to choose this over follow_up_cadence, rewrite_follow_up_text, or write_follow_up_texts, nor any exclusions. Context is present but no explicit routing guidance, so this is implied usage rather than 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?

Annotations declare readOnlyHint=true and openWorldHint=true, so the agent already knows this is a safe, non-mutating operation. The description adds valuable behavioral context: it produces exactly two texts, enforces a length limit, and imposes content rules (one question, a way out, no price/payment/discount). This goes beyond the annotations and helps the agent set expectations. It does not mention output format, but with no output schema, that is a minor gap.

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, dense sentence that front-loads the core action ('Writes two follow-up texts') and then lists the key constraints in a compact, scannable list. Every phrase earns its place; there is no filler or repetition of schema field names.

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 generation tool with no output schema, the description covers the essential behavioral contract: what it produces, how many, length limit, and content constraints. It does not specify the output format (e.g., plain text vs. structured list), which an agent might need to know, but the constraints are detailed enough for most use cases. The openWorldHint annotation also signals that the tool may accept flexible inputs, which the description supports by saying 'a sales situation you describe.'

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 17% (only 'situation' has a description), so the description must compensate. It does: it explains that the tool takes a sales situation and produces texts with specific constraints. However, it does not clarify the meaning of parameters like 'rep', 'company', 'product', 'day_and_time', or 'customer_first_name' beyond their names. The description's content rules (names the rep and company) imply some parameter usage, but explicit mapping would be stronger.

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 ('writes'), a specific resource ('two follow-up texts'), and the exact context ('for a sales situation you describe'). It also lists concrete content constraints (under 300 characters, names rep and company, one question, a way out, no price/payment/discount), which makes the tool's purpose unmistakable and distinguishes it from siblings like rewrite_follow_up_text or check_follow_up_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?

The description clearly implies when to use this tool: when you need to generate two follow-up texts for a sales situation. It does not explicitly name alternatives or exclusions, but the sibling list includes rewrite_follow_up_text and check_follow_up_text, and the description's focus on 'writes two' makes the use case clear. It could be improved by explicitly saying 'use rewrite_follow_up_text to revise an existing text' or 'use check_follow_up_text to evaluate a text.'

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